Morten Hjorth-Jensen
1476 lines
64 KiB
Plaintext
1476 lines
64 KiB
Plaintext
\begin{thebibliography}{208}
|
||
\providecommand{\natexlab}[1]{#1}
|
||
\providecommand{\url}[1]{\texttt{#1}}
|
||
\expandafter\ifx\csname urlstyle\endcsname\relax
|
||
\providecommand{\doi}[1]{doi: #1}\else
|
||
\providecommand{\doi}{doi: \begingroup \urlstyle{rm}\Url}\fi
|
||
|
||
\bibitem[Abadi et~al.(2016)Abadi, Agarwal, Barham, Brevdo, Chen, Citro,
|
||
Corrado, Davis, Dean, Devin, et~al.]{abadi2016tensorflow}
|
||
Mart{\'\i}n Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen,
|
||
Craig Citro, Greg~S Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, et~al.
|
||
\newblock {TensorFlow}: Large-scale machine learning on heterogeneous
|
||
distributed systems.
|
||
\newblock \emph{arXiv preprint arXiv:1603.04467}, 2016.
|
||
|
||
\bibitem[Adamson and Winant(1969)]{Adamson1969}
|
||
D.~S. Adamson and C.~W. Winant.
|
||
\newblock A {SLANG} simulation of an initially strong shock wave downstream of
|
||
an infinite area change.
|
||
\newblock In \emph{Proceedings of the Conference on Applications of
|
||
Continuous-System Simulation Languages}, pages 231--40, 1969.
|
||
|
||
\bibitem[Agarwal et~al.(2016)Agarwal, Bullins, and Hazan]{agarwal2016second}
|
||
Naman Agarwal, Brian Bullins, and Elad Hazan.
|
||
\newblock Second order stochastic optimization in linear time.
|
||
\newblock Technical Report arXiv:1602.03943, arXiv preprint, 2016.
|
||
|
||
\bibitem[{Al Seyab} and Cao(2008)]{AlSeyab2008}
|
||
R.~K. {Al Seyab} and Y.~Cao.
|
||
\newblock Nonlinear system identification for predictive control using
|
||
continuous time recurrent neural networks and automatic differentiation.
|
||
\newblock \emph{Journal of Process Control}, 18\penalty0 (6):\penalty0
|
||
568--581, 2008.
|
||
\newblock \doi{10.1016/j.jprocont.2007.10.012}.
|
||
|
||
\bibitem[Amos and Kolter(2017)]{amos2017optnet}
|
||
Brandon Amos and J~Zico Kolter.
|
||
\newblock {OptNet}: Differentiable optimization as a layer in neural networks.
|
||
\newblock \emph{arXiv preprint arXiv:1703.00443}, 2017.
|
||
|
||
\bibitem[Apostolopoulou et~al.(2009)Apostolopoulou, Sotiropoulos, Livieris, and
|
||
Pintelas]{Apostolopoulou2009}
|
||
Marianna~S. Apostolopoulou, Dimitris~G. Sotiropoulos, Ioannis~E. Livieris, and
|
||
Panagiotis Pintelas.
|
||
\newblock A memoryless {BFGS} neural network training algorithm.
|
||
\newblock In \emph{7th IEEE International Conference on Industrial Informatics,
|
||
INDIN 2009}, pages 216--221, June 2009.
|
||
\newblock \doi{10.1109/INDIN.2009.5195806}.
|
||
|
||
\bibitem[Appel(1989)]{appel1989runtime}
|
||
Andrew~W Appel.
|
||
\newblock Runtime tags aren't necessary.
|
||
\newblock \emph{Lisp and Symbolic Computation}, 2\penalty0 (2):\penalty0
|
||
153--162, 1989.
|
||
|
||
\bibitem[Bahdanau et~al.(2014)Bahdanau, Cho, and Bengio]{bahdanau2014neural}
|
||
Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio.
|
||
\newblock Neural machine translation by jointly learning to align and
|
||
translate.
|
||
\newblock \emph{arXiv preprint arXiv:1409.0473}, 2014.
|
||
|
||
\bibitem[Barrett and Siskind(2013)]{Barrett2013}
|
||
Daniel~Paul Barrett and Jeffrey~Mark Siskind.
|
||
\newblock {Felzenszwalb-Baum-Welch}: Event detection by changing appearance.
|
||
\newblock \emph{arXiv preprint arXiv:1306.4746}, 2013.
|
||
|
||
\bibitem[Bastien et~al.(2012)Bastien, Lamblin, Pascanu, Bergstra, Goodfellow,
|
||
Bergeron, Bouchard, Warde-Farley, and Bengio]{Bastien2012}
|
||
Frédéric Bastien, Pascal Lamblin, Razvan Pascanu, James Bergstra, Ian
|
||
Goodfellow, Arnaud Bergeron, Nicolas Bouchard, David Warde-Farley, and Yoshua
|
||
Bengio.
|
||
\newblock Theano: new features and speed improvements.
|
||
\newblock Deep Learning and Unsupervised Feature Learning NIPS 2012 Workshop,
|
||
2012.
|
||
|
||
\bibitem[Bauer(1974)]{Bauer1974}
|
||
Friedrich~L. Bauer.
|
||
\newblock Computational graphs and rounding error.
|
||
\newblock \emph{SIAM Journal on Numerical Analysis}, 11\penalty0 (1):\penalty0
|
||
87--96, 1974.
|
||
|
||
\bibitem[Baydin et~al.(2016{\natexlab{a}})Baydin, Pearlmutter, and
|
||
Siskind]{baydin2016diffsharp}
|
||
Atılım~Güneş Baydin, Barak~A. Pearlmutter, and Jeffrey~Mark Siskind.
|
||
\newblock Diffsharp: An {AD} library for {.NET} languages.
|
||
\newblock In \emph{7th International Conference on Algorithmic Differentiation,
|
||
Christ Church Oxford, UK, September 12--15, 2016}, 2016{\natexlab{a}}.
|
||
\newblock Also arXiv:1611.03423.
|
||
|
||
\bibitem[Baydin et~al.(2016{\natexlab{b}})Baydin, Pearlmutter, and
|
||
Siskind]{baydin2016tricks}
|
||
Atılım~Güneş Baydin, Barak~A. Pearlmutter, and Jeffrey~Mark Siskind.
|
||
\newblock Tricks from deep learning.
|
||
\newblock In \emph{7th International Conference on Algorithmic Differentiation,
|
||
Christ Church Oxford, UK, September 12--15, 2016}, 2016{\natexlab{b}}.
|
||
\newblock Also arXiv:1611.03777.
|
||
|
||
\bibitem[Baydin et~al.(2018)Baydin, Cornish, Rubio, Schmidt, and
|
||
Wood]{baydin2017online}
|
||
Atılım~Güneş Baydin, Robert Cornish, David~Martínez Rubio, Mark Schmidt,
|
||
and Frank Wood.
|
||
\newblock Online learning rate adaptation with hypergradient descent.
|
||
\newblock In \emph{Sixth International Conference on Learning Representations
|
||
(ICLR), Vancouver, Canada, April 30--May 3, 2018}, 2018.
|
||
|
||
\bibitem[Beda et~al.(1959)Beda, Korolev, Sukkikh, and Frolova]{Beda1959}
|
||
L.~M. Beda, L.~N. Korolev, N.~V. Sukkikh, and T.~S. Frolova.
|
||
\newblock Programs for automatic differentiation for the machine {BESM} (in
|
||
{Russian}).
|
||
\newblock Technical report, Institute for Precise Mechanics and Computation
|
||
Techniques, Academy of Science, Moscow, USSR, 1959.
|
||
|
||
\bibitem[Bell and Burke(2008)]{Bell2008}
|
||
Bradley~M. Bell and James~V. Burke.
|
||
\newblock Algorithmic differentiation of implicit functions and optimal values.
|
||
\newblock In C.~H. Bischof, H.~M. Bücker, P.~Hovland, U.~Naumann, and J.~Utke,
|
||
editors, \emph{Advances in Automatic Differentiation}, volume~64 of
|
||
\emph{Lecture Notes in Computational Science and Engineering}, pages 67--77.
|
||
Springer Berlin Heidelberg, 2008.
|
||
\newblock \doi{10.1007/978-3-540-68942-3_7}.
|
||
|
||
\bibitem[Bendtsen and Stauning(1996)]{Bendtsen1996}
|
||
Claus Bendtsen and Ole Stauning.
|
||
\newblock {FADBAD}, a flexible {C++} package for automatic differentiation.
|
||
\newblock Technical Report IMM-REP-1996-17, Department of Mathematical
|
||
Modelling, Technical University of Denmark, Lyngby, Denmark, 1996.
|
||
|
||
\bibitem[Bengio et~al.(2013)Bengio, Courville, and
|
||
Vincent]{bengio2013representation}
|
||
Yoshua Bengio, Aaron Courville, and Pascal Vincent.
|
||
\newblock Representation learning: A review and new perspectives.
|
||
\newblock \emph{{IEEE} Transactions on Pattern Analysis and Machine
|
||
Intelligence}, 35\penalty0 (8):\penalty0 1798--1828, 2013.
|
||
|
||
\bibitem[Bert and Malik(1996)]{Bert1996}
|
||
Charles~W. Bert and Moinuddin Malik.
|
||
\newblock Differential quadrature method in computational mechanics: A review.
|
||
\newblock \emph{Applied Mechanics Reviews}, 49, 1996.
|
||
\newblock \doi{10.1115/1.3101882}.
|
||
|
||
\bibitem[Berz et~al.(1996)Berz, Makino, Shamseddine, Hoffstätter, and
|
||
Wan]{Berz1996}
|
||
Martin Berz, Kyoko Makino, Khodr Shamseddine, Georg~H. Hoffstätter, and Weishi
|
||
Wan.
|
||
\newblock {COSY} {INFINITY} and its applications in nonlinear dynamics.
|
||
\newblock In M.~Berz, C.~Bischof, G.~Corliss, and A.~Griewank, editors,
|
||
\emph{Computational Differentiation: Techniques, Applications, and Tools},
|
||
pages 363--5. Society for Industrial and Applied Mathematics, Philadelphia,
|
||
PA, 1996.
|
||
|
||
\bibitem[Bischof et~al.(1996)Bischof, Carle, Corliss, Griewank, and
|
||
Hovland]{Bischof1996}
|
||
Christian Bischof, Alan Carle, George Corliss, Andreas Griewank, and Paul
|
||
Hovland.
|
||
\newblock {ADIFOR} 2.0: Automatic differentiation of {Fortran} 77 programs.
|
||
\newblock \emph{Computational Science Engineering, IEEE}, 3\penalty0
|
||
(3):\penalty0 18--32, 1996.
|
||
\newblock \doi{10.1109/99.537089}.
|
||
|
||
\bibitem[Bischof et~al.(1997)Bischof, Roh, and {Mauer-Oats}]{Bischof1997}
|
||
Christian Bischof, Lucas Roh, and Andrew {Mauer-Oats}.
|
||
\newblock {ADIC}: An extensible automatic differentiation tool for {ANSI-C}.
|
||
\newblock \emph{Software Practice and Experience}, 27\penalty0 (12):\penalty0
|
||
1427--56, 1997.
|
||
|
||
\bibitem[Bischof et~al.(2002)Bischof, Bücker, and Lang]{Bischof2002}
|
||
Christian~H. Bischof, H.~Martin Bücker, and Bruno Lang.
|
||
\newblock Automatic differentiation for computational finance.
|
||
\newblock In E.~J. Kontoghiorghes, B.~Rustem, and S.~Siokos, editors,
|
||
\emph{Computational Methods in Decision-Making, Economics and Finance},
|
||
volume~74 of \emph{Applied Optimization}, pages 297--310. Springer US, 2002.
|
||
\newblock \doi{10.1007/978-1-4757-3613-7_15}.
|
||
|
||
\bibitem[Bischof et~al.(2006)Bischof, Bücker, Rasch, Slusanschi, and
|
||
Lang]{Bischof2006}
|
||
Christian~H. Bischof, H.~Martin Bücker, Arno Rasch, Emil Slusanschi, and Bruno
|
||
Lang.
|
||
\newblock Automatic differentiation of the general-purpose computational fluid
|
||
dynamics package {FLUENT}.
|
||
\newblock \emph{Journal of Fluids Engineering}, 129\penalty0 (5):\penalty0
|
||
652--8, 2006.
|
||
\newblock \doi{10.1115/1.2720475}.
|
||
|
||
\bibitem[Bischof et~al.(2008)Bischof, Hovland, and Norris]{Bischof2008}
|
||
Christian~H. Bischof, Paul~D. Hovland, and Boyana Norris.
|
||
\newblock On the implementation of automatic differentiation tools.
|
||
\newblock \emph{Higher-Order and Symbolic Computation}, 21\penalty0
|
||
(3):\penalty0 311--31, 2008.
|
||
\newblock \doi{10.1007/s10990-008-9034-4}.
|
||
|
||
\bibitem[Boltyanskii et~al.(1960)Boltyanskii, Gamkrelidze, and
|
||
Pontryagin]{Boltyanskii-Gamkrelidze-Pontryagin-1960a}
|
||
V.~G. Boltyanskii, R.~V. Gamkrelidze, and L.~S. Pontryagin.
|
||
\newblock The theory of optimal processes {I}: The maximum principle.
|
||
\newblock \emph{Izvest. Akad. Nauk S.S.S.R. Ser. Mat.}, 24:\penalty0 3--42,
|
||
1960.
|
||
|
||
\bibitem[Bottou(2010)]{bottou2010large}
|
||
L{\'e}on Bottou.
|
||
\newblock Large-scale machine learning with stochastic gradient descent.
|
||
\newblock In \emph{Proceedings of COMPSTAT'2010}, pages 177--186. Springer,
|
||
2010.
|
||
|
||
\bibitem[Bottou and {LeCun}(1988)]{bottou-lecun-88}
|
||
{L\'eon} Bottou and Yann {LeCun}.
|
||
\newblock {SN}: A simulator for connectionist models.
|
||
\newblock In \emph{Proceedings of NeuroNimes 88}, pages 371--382, Nimes,
|
||
France, 1988.
|
||
\newblock URL \url{http://leon.bottou.org/papers/bottou-lecun-88}.
|
||
|
||
\bibitem[Bottou and LeCun(2002)]{LUSH2002}
|
||
L\'{e}on Bottou and Yann LeCun.
|
||
\newblock Lush reference manual, 2002.
|
||
\newblock URL \url{http://lush.sourceforge.net/doc.html}.
|
||
|
||
\bibitem[Bottou et~al.(2016)Bottou, Curtis, and
|
||
Nocedal]{bottou2016optimization}
|
||
L{\'e}on Bottou, Frank~E. Curtis, and Jorge Nocedal.
|
||
\newblock Optimization methods for large-scale machine learning.
|
||
\newblock \emph{arXiv preprint arXiv:1606.04838}, 2016.
|
||
|
||
\bibitem[Bottou(1998)]{Bottou1998}
|
||
Léon Bottou.
|
||
\newblock Online learning and stochastic approximations.
|
||
\newblock \emph{On-Line Learning in Neural Networks}, 17:\penalty0 9, 1998.
|
||
|
||
\bibitem[Brezinski and Zaglia(1991)]{Brezinski1991}
|
||
Claude Brezinski and M.~Redivo Zaglia.
|
||
\newblock \emph{Extrapolation Methods: Theory and Practice}.
|
||
\newblock North-Holland, 1991.
|
||
|
||
\bibitem[Bryson and Denham(1962)]{Bryson-1962a}
|
||
A.~E. Bryson and W.~F. Denham.
|
||
\newblock A steepest ascent method for solving optimum programming problems.
|
||
\newblock \emph{Journal of Applied Mechanics}, 29\penalty0 (2):\penalty0 247,
|
||
1962.
|
||
\newblock \doi{10.1115/1.3640537}.
|
||
|
||
\bibitem[Bryson and Ho(1969)]{Bryson-Ho-1969a}
|
||
Arthur~E. Bryson and Yu-Chi Ho.
|
||
\newblock \emph{Applied Optimal Control: Optimization, Estimation, and
|
||
Control}.
|
||
\newblock Blaisdell, Waltham, MA, 1969.
|
||
|
||
\bibitem[Burden and Faires(2001)]{Burden2001}
|
||
Rirchard~L. Burden and J.~Douglas Faires.
|
||
\newblock \emph{Numerical Analysis}.
|
||
\newblock Brooks/Cole, 2001.
|
||
|
||
\bibitem[Capriotti(2011)]{Capriotti2011}
|
||
Luca Capriotti.
|
||
\newblock Fast {Greeks} by algorithmic differentiation.
|
||
\newblock \emph{Journal of Computational Finance}, 14\penalty0 (3):\penalty0 3,
|
||
2011.
|
||
|
||
\bibitem[Carmichael and Sandu(1997)]{Carmichael1997}
|
||
Gregory~R. Carmichael and Adrian Sandu.
|
||
\newblock Sensitivity analysis for atmospheric chemistry models via automatic
|
||
differentiation.
|
||
\newblock \emph{Atmospheric Environment}, 31\penalty0 (3):\penalty0 475--89,
|
||
1997.
|
||
|
||
\bibitem[Carpenter et~al.(2015)Carpenter, Hoffman, Brubaker, Lee, Li, and
|
||
Betancourt]{carpenter2015stan}
|
||
Bob Carpenter, Matthew~D Hoffman, Marcus Brubaker, Daniel Lee, Peter Li, and
|
||
Michael Betancourt.
|
||
\newblock The {Stan} math library: Reverse-mode automatic differentiation in
|
||
{C++}.
|
||
\newblock \emph{arXiv preprint arXiv:1509.07164}, 2015.
|
||
|
||
\bibitem[Carpenter et~al.(2016)Carpenter, Gelman, Hoffman, Lee, Goodrich,
|
||
Betancourt, Brubaker, Guo, Li, and Riddell]{carpenter2016stan}
|
||
Bob Carpenter, Andrew Gelman, Matt Hoffman, Daniel Lee, Ben Goodrich, Michael
|
||
Betancourt, Michael~A Brubaker, Jiqiang Guo, Peter Li, and Allen Riddell.
|
||
\newblock Stan: A probabilistic programming language.
|
||
\newblock \emph{Journal of Statistical Software}, 20:\penalty0 1--37, 2016.
|
||
|
||
\bibitem[Casanova et~al.(2002)Casanova, Sharp, Final, Christianson, and
|
||
Symonds]{casanova2002application}
|
||
Daniele Casanova, Robin~S. Sharp, Mark Final, Bruce Christianson, and Pat
|
||
Symonds.
|
||
\newblock Application of automatic diffentiation to race car performance
|
||
optimisation.
|
||
\newblock In George Corliss, Christ\`{e}le Faure, Andreas Griewank, Lauren
|
||
Hasco\"{e}t, and Uwe Naumann, editors, \emph{Automatic Differentiation of
|
||
Algorithms}, pages 117--124. Springer-Verlag New York, Inc., New York, NY,
|
||
USA, 2002.
|
||
\newblock ISBN 0-387-95305-1.
|
||
|
||
\bibitem[Charpentier and Ghemires(2000)]{Charpentier2000}
|
||
Isabelle Charpentier and Mohammed Ghemires.
|
||
\newblock Efficient adjoint derivatives: Application to the meteorological
|
||
model {Meso-NH}.
|
||
\newblock \emph{Optimization Methods and Software}, 13\penalty0 (1):\penalty0
|
||
35--63, 2000.
|
||
|
||
\bibitem[Chen and Manning(2014)]{chen2014fast}
|
||
Danqi Chen and Christopher Manning.
|
||
\newblock A fast and accurate dependency parser using neural networks.
|
||
\newblock In \emph{Proceedings of the 2014 Conference on Empirical Methods in
|
||
Natural Language Processing (EMNLP)}, pages 740--750, 2014.
|
||
|
||
\bibitem[Chetlur et~al.(2014)Chetlur, Woolley, Vandermersch, Cohen, Tran,
|
||
Catanzaro, and Shelhamer]{chetlur2014cudnn}
|
||
Sharan Chetlur, Cliff Woolley, Philippe Vandermersch, Jonathan Cohen, John
|
||
Tran, Bryan Catanzaro, and Evan Shelhamer.
|
||
\newblock {cuDNN}: Efficient primitives for deep learning.
|
||
\newblock \emph{arXiv preprint arXiv:1410.0759}, 2014.
|
||
|
||
\bibitem[Chib and Greenberg(1995)]{Chib1995}
|
||
Siddhartha Chib and Edward Greenberg.
|
||
\newblock Understanding the {Metropolis-Hastings} algorithm.
|
||
\newblock \emph{The American Statistician}, 49\penalty0 (4):\penalty0 327--335,
|
||
1995.
|
||
\newblock \doi{10.1080/00031305.1995.10476177}.
|
||
|
||
\bibitem[Christianson(1994)]{christianson1994reverse}
|
||
Bruce Christianson.
|
||
\newblock Reverse accumulation and attractive fixed points.
|
||
\newblock \emph{Optimization Methods and Software}, 3\penalty0 (4):\penalty0
|
||
311--326, 1994.
|
||
|
||
\bibitem[Christianson(2012)]{Christianson2012ALN}
|
||
Bruce Christianson.
|
||
\newblock A {L}eibniz notation for automatic differentiation.
|
||
\newblock In Shaun Forth, Paul Hovland, Eric Phipps, Jean Utke, and Andrea
|
||
Walther, editors, \emph{Recent Advances in Algorithmic Differentiation},
|
||
volume~87 of \emph{Lecture Notes in Computational Science and Engineering},
|
||
pages 1--9. Springer, Berlin, 2012.
|
||
\newblock ISBN 978-3-540-68935-5.
|
||
\newblock \doi{10.1007/978-3-642-30023-3_1}.
|
||
|
||
\bibitem[Clifford(1873)]{Clifford1873}
|
||
William~K. Clifford.
|
||
\newblock Preliminary sketch of bi-quaternions.
|
||
\newblock \emph{Proceedings of the London Mathematical Society}, 4:\penalty0
|
||
381--95, 1873.
|
||
|
||
\bibitem[Cohen and Molemaker(2009)]{cohen2009fast}
|
||
J~Cohen and M~Jeroen Molemaker.
|
||
\newblock A fast double precision cfd code using cuda.
|
||
\newblock \emph{Parallel Computational Fluid Dynamics: Recent Advances and
|
||
Future Directions}, pages 414--429, 2009.
|
||
|
||
\bibitem[Collobert et~al.(2011)Collobert, Kavukcuoglu, and
|
||
Farabet]{collobert2011torch7}
|
||
Ronan Collobert, Koray Kavukcuoglu, and Cl{\'e}ment Farabet.
|
||
\newblock Torch7: A {Matlab}-like environment for machine learning.
|
||
\newblock In \emph{BigLearn, NIPS Workshop}, number EPFL-CONF-192376, 2011.
|
||
|
||
\bibitem[Corliss(1988)]{Corliss1988}
|
||
George~F. Corliss.
|
||
\newblock \emph{Application of differentiation arithmetic}, volume~19 of
|
||
\emph{Perspectives in Computing}, pages 127--48.
|
||
\newblock Academic Press, Boston, 1988.
|
||
|
||
\bibitem[Courbariaux et~al.(2015)Courbariaux, Bengio, and
|
||
David]{courbariaux2015binaryconnect}
|
||
Matthieu Courbariaux, Yoshua Bengio, and Jean-Pierre David.
|
||
\newblock Binaryconnect: Training deep neural networks with binary weights
|
||
during propagations.
|
||
\newblock In \emph{Advances in Neural Information Processing Systems}, pages
|
||
3123--3131, 2015.
|
||
|
||
\bibitem[Dalal and Triggs(2005)]{Dalal2005}
|
||
Navneet Dalal and Bill Triggs.
|
||
\newblock Histograms of oriented gradients for human detection.
|
||
\newblock In \emph{Proceedings of the 2005 IEEE Computer Society Conference on
|
||
Computer Vision and Pattern Recognition (CVPR'05)}, pages 886--93,
|
||
Washington, DC, USA, 2005. IEEE Computer Society.
|
||
\newblock \doi{10.1109/CVPR.2005.177}.
|
||
|
||
\bibitem[Dauvergne and Hasco{\"e}t(2006)]{Dauvergne2006}
|
||
Benjamin Dauvergne and Laurent Hasco{\"e}t.
|
||
\newblock The data-flow equations of checkpointing in reverse automatic
|
||
differentiation.
|
||
\newblock In V.~N. Alexandrov, G.~D. {van Albada}, P.~M.~A. Sloot, and
|
||
J.~Dongarra, editors, \emph{Computational Science – ICCS 2006}, volume 3994
|
||
of \emph{Lecture Notes in Computer Science}, pages 566--73, Dauvergne, 2006.
|
||
Springer Berlin.
|
||
|
||
\bibitem[Dennis and Schnabel(1996)]{Dennis1996}
|
||
John~E. Dennis and Robert~B. Schnabel.
|
||
\newblock \emph{Numerical Methods for Unconstrained Optimization and Nonlinear
|
||
Equations}.
|
||
\newblock Classics in Applied Mathematics. Society for Industrial and Applied
|
||
Mathematics, Philadelphia, 1996.
|
||
|
||
\bibitem[Dixon(1991)]{Dixon1991}
|
||
L.~C. Dixon.
|
||
\newblock Use of automatic differentiation for calculating {Hessians} and
|
||
{Newton} steps.
|
||
\newblock In A.~Griewank and G.~F. Corliss, editors, \emph{Automatic
|
||
Differentiation of Algorithms: Theory, Implementation, and Application},
|
||
pages 114--125. SIAM, Philadelphia, PA, 1991.
|
||
|
||
\bibitem[Duane et~al.(1987)Duane, Kennedy, Pendleton, and Roweth]{Duane1987}
|
||
Simon Duane, Anthony~D. Kennedy, Brian~J. Pendleton, and Duncan Roweth.
|
||
\newblock Hybrid {Monte Carlo}.
|
||
\newblock \emph{Physics Letters B}, 195\penalty0 (2):\penalty0 216--222, 1987.
|
||
|
||
\bibitem[Duchi et~al.(2011)Duchi, Hazan, and Singer]{duchi2011adaptive}
|
||
John Duchi, Elad Hazan, and Yoram Singer.
|
||
\newblock Adaptive subgradient methods for online learning and stochastic
|
||
optimization.
|
||
\newblock \emph{Journal of Machine Learning Research}, 12\penalty0
|
||
(Jul):\penalty0 2121--2159, 2011.
|
||
|
||
\bibitem[Ekstr{\"o}m et~al.(2010)Ekstr{\"o}m, Visscher, Bast, Thorvaldsen, and
|
||
Ruud]{Ekstrom2010}
|
||
Ulf Ekstr{\"o}m, Lucas Visscher, Radovan Bast, Andreas~J. Thorvaldsen, and
|
||
Kenneth Ruud.
|
||
\newblock Arbitrary-order density functional response theory from automatic
|
||
differentiation.
|
||
\newblock \emph{Journal of Chemical Theory and Computation}, 6:\penalty0
|
||
1971--80, 2010.
|
||
\newblock \doi{10.1021/ct100117s}.
|
||
|
||
\bibitem[Eriksson et~al.(1998)Eriksson, Gulliksson, Lindström, and Åke
|
||
Wedin]{Eriksson1998}
|
||
Jerry Eriksson, Mårten Gulliksson, Per Lindström, and Per Åke Wedin.
|
||
\newblock Regularization tools for training large feed-forward neural networks
|
||
using automatic differentiation.
|
||
\newblock \emph{Optimization Methods and Software}, 10\penalty0 (1):\penalty0
|
||
49--69, 1998.
|
||
\newblock \doi{10.1080/10556789808805701}.
|
||
|
||
\bibitem[Eslami et~al.(2016)Eslami, Heess, Weber, Tassa, Szepesvari,
|
||
Kavukcuoglu, and Hinton]{eslami2016attend}
|
||
S.~M.~Ali Eslami, Nicolas Heess, Theophane Weber, Yuval Tassa, David
|
||
Szepesvari, Koray Kavukcuoglu, and Geoffrey~E. Hinton.
|
||
\newblock Attend, infer, repeat: Fast scene understanding with generative
|
||
models.
|
||
\newblock In D.~D. Lee, M.~Sugiyama, U.~V. Luxburg, I.~Guyon, and R.~Garnett,
|
||
editors, \emph{Advances in Neural Information Processing Systems 29}, pages
|
||
3225--3233. Curran Associates, Inc., 2016.
|
||
|
||
\bibitem[Finkel et~al.(2008)Finkel, Kleeman, and Manning]{Finkel2008}
|
||
Jenny~Rose Finkel, Alex Kleeman, and Christopher~D. Manning.
|
||
\newblock Efficient, feature-based, conditional random field parsing.
|
||
\newblock In \emph{Proceedings of the 46th Annual Meeting of the Association
|
||
for Computational Linguistics (ACL 2008)}, pages 959--67, 2008.
|
||
|
||
\bibitem[Fornberg(1981)]{Fornberg1981}
|
||
Bengt Fornberg.
|
||
\newblock Numerical differentiation of analytic functions.
|
||
\newblock \emph{ACM Transactions on Mathematical Software}, 7\penalty0
|
||
(4):\penalty0 512--26, 1981.
|
||
\newblock \doi{10.1145/355972.355979}.
|
||
|
||
\bibitem[Forth(2006)]{Forth2006}
|
||
Shaun~A. Forth.
|
||
\newblock An efficient overloaded implementation of forward mode automatic
|
||
differentiation in {MATLAB}.
|
||
\newblock \emph{ACM Transactions on Mathematical Software}, 32\penalty0
|
||
(2):\penalty0 195--222, 2006.
|
||
|
||
\bibitem[Forth and Evans(2002)]{forth2002aerofoil}
|
||
Shaun~A. Forth and Trevor~P. Evans.
|
||
\newblock Aerofoil optimisation via {AD} of a multigrid cell-vertex {Euler}
|
||
flow solver.
|
||
\newblock In George Corliss, Christ{\`e}le Faure, Andreas Griewank, Laurent
|
||
Hasco{\"e}t, and Uwe Naumann, editors, \emph{Automatic Differentiation of
|
||
Algorithms: From Simulation to Optimization}, pages 153--160. Springer New
|
||
York, New York, NY, 2002.
|
||
\newblock ISBN 978-1-4613-0075-5.
|
||
\newblock \doi{10.1007/978-1-4613-0075-5_17}.
|
||
|
||
\bibitem[Fourer et~al.(2002)Fourer, Gay, and Kernighan]{Fourer2002}
|
||
Robert Fourer, David~M. Gay, and Brian~W. Kernighan.
|
||
\newblock \emph{{AMPL}: A Modeling Language for Mathematical Programming}.
|
||
\newblock Duxbury Press, 2002.
|
||
|
||
\bibitem[Gay(1996)]{Gay1996}
|
||
David~M. Gay.
|
||
\newblock Automatically finding and exploiting partially separable structure in
|
||
nonlinear programming problems.
|
||
\newblock Technical report, Bell Laboratories, Murray Hill, NJ, 1996.
|
||
|
||
\bibitem[Gebremedhin et~al.(2009)Gebremedhin, Tarafdar, Pothen, and
|
||
Walther]{Gebremedhin2009}
|
||
Assefaw~H. Gebremedhin, Arijit Tarafdar, Alex Pothen, and Andrea Walther.
|
||
\newblock Efficient computation of sparse {Hessians} using coloring and
|
||
automatic differentiation.
|
||
\newblock \emph{INFORMS Journal on Computing}, 21\penalty0 (2):\penalty0
|
||
209--23, 2009.
|
||
\newblock \doi{10.1287/ijoc.1080.0286}.
|
||
|
||
\bibitem[Gebremedhin et~al.(2013)Gebremedhin, Nguyen, Patwary, and
|
||
Pothen]{gebremedhin2013colpack}
|
||
Assefaw~H Gebremedhin, Duc Nguyen, Md~Mostofa~Ali Patwary, and Alex Pothen.
|
||
\newblock {ColPack}: Software for graph coloring and related problems in
|
||
scientific computing.
|
||
\newblock \emph{ACM Transactions on Mathematical Software (TOMS)}, 40\penalty0
|
||
(1):\penalty0 1, 2013.
|
||
|
||
\bibitem[Gershman and Goodman(2014)]{gershman2014amortized}
|
||
Samuel Gershman and Noah Goodman.
|
||
\newblock Amortized inference in probabilistic reasoning.
|
||
\newblock In \emph{Proceedings of the Annual Meeting of the Cognitive Science
|
||
Society}, number~36, 2014.
|
||
|
||
\bibitem[Giering and Kaminski(1998)]{Giering1998}
|
||
Ralf Giering and Thomas Kaminski.
|
||
\newblock Recipes for adjoint code construction.
|
||
\newblock \emph{ACM Transactions on Mathematical Software}, 24:\penalty0
|
||
437--74, 1998.
|
||
\newblock \doi{10.1145/293686.293695}.
|
||
|
||
\bibitem[Gimpel et~al.(2010)Gimpel, Das, and Smith]{Gimpel2010}
|
||
Kevin Gimpel, Dipanjan Das, and Noah~A. Smith.
|
||
\newblock Distributed asynchronous online learning for natural language
|
||
processing.
|
||
\newblock In \emph{Proceedings of the Fourteenth Conference on Computational
|
||
Natural Language Learning}, CoNLL '10, pages 213--222, Stroudsburg, PA, USA,
|
||
2010. Association for Computational Linguistics.
|
||
|
||
\bibitem[Girolami and Calderhead(2011)]{Girolami2011}
|
||
Mark Girolami and Be~Calderhead.
|
||
\newblock Riemann manifold {Langevin} and {Hamiltonian} {Monte Carlo} methods.
|
||
\newblock \emph{Journal of the Royal Statistical Society: Series B (Statistical
|
||
Methodology)}, 73\penalty0 (2):\penalty0 123--214, 2011.
|
||
|
||
\bibitem[Goldberg(2016)]{goldberg2016primer}
|
||
Yoav Goldberg.
|
||
\newblock A primer on neural network models for natural language processing.
|
||
\newblock \emph{Journal of Artificial Intelligence Research}, 57:\penalty0
|
||
345--420, 2016.
|
||
|
||
\bibitem[Goodfellow et~al.(2016)Goodfellow, Bengio, and
|
||
Courville]{goodfellow2016deep}
|
||
Ian Goodfellow, Yoshua Bengio, and Aaron Courville.
|
||
\newblock \emph{Deep Learning}.
|
||
\newblock MIT Press, 2016.
|
||
\newblock \url{http://www.deeplearningbook.org}.
|
||
|
||
\bibitem[Gordon et~al.(2014)Gordon, Henzinger, Nori, and
|
||
Rajamani]{gordon2014probabilistic}
|
||
Andrew~D Gordon, Thomas~A Henzinger, Aditya~V Nori, and Sriram~K Rajamani.
|
||
\newblock Probabilistic programming.
|
||
\newblock In \emph{Proceedings of the on Future of Software Engineering}, pages
|
||
167--181. ACM, 2014.
|
||
|
||
\bibitem[Grabmeier and Kaltofen(2003)]{Grabmeier2003}
|
||
Johannes Grabmeier and Erich Kaltofen.
|
||
\newblock \emph{Computer Algebra Handbook: Foundations, Applications, Systems}.
|
||
\newblock Springer, 2003.
|
||
|
||
\bibitem[Grabner et~al.(2008)Grabner, Pock, Gross, and Kainz]{Grabner2008}
|
||
Markus Grabner, Thomas Pock, Tobias Gross, and Bernhard Kainz.
|
||
\newblock Automatic differentiation for {GPU}-accelerated {2D/3D} registration.
|
||
\newblock In C.~H. Bischof, H.~M. Bücker, P.~Hovland, U.~Naumann, and J.~Utke,
|
||
editors, \emph{Advances in Automatic Differentiation}, volume~64 of
|
||
\emph{Lecture Notes in Computational Science and Engineering}, pages
|
||
259--269. Springer Berlin Heidelberg, 2008.
|
||
\newblock \doi{10.1007/978-3-540-68942-3_23}.
|
||
|
||
\bibitem[Grathwohl et~al.(2017)Grathwohl, Choi, Wu, Roeder, and
|
||
Duvenaud]{grathwohl2017backpropagation}
|
||
Will Grathwohl, Dami Choi, Yuhuai Wu, Geoff Roeder, and David Duvenaud.
|
||
\newblock Backpropagation through the void: Optimizing control variates for
|
||
black-box gradient estimation.
|
||
\newblock \emph{arXiv preprint arXiv:1711.00123}, 2017.
|
||
|
||
\bibitem[Graves et~al.(2014)Graves, Wayne, and Danihelka]{graves2014neural}
|
||
Alex Graves, Greg Wayne, and Ivo Danihelka.
|
||
\newblock Neural {Turing} machines.
|
||
\newblock \emph{arXiv preprint arXiv:1410.5401}, 2014.
|
||
|
||
\bibitem[Graves et~al.(2016)Graves, Wayne, Reynolds, Harley, Danihelka,
|
||
Grabska-Barwi{\'n}ska, Colmenarejo, Grefenstette, Ramalho, Agapiou,
|
||
et~al.]{graves2016hybrid}
|
||
Alex Graves, Greg Wayne, Malcolm Reynolds, Tim Harley, Ivo Danihelka, Agnieszka
|
||
Grabska-Barwi{\'n}ska, Sergio~G{\'o}mez Colmenarejo, Edward Grefenstette,
|
||
Tiago Ramalho, John Agapiou, et~al.
|
||
\newblock Hybrid computing using a neural network with dynamic external memory.
|
||
\newblock \emph{Nature}, 538\penalty0 (7626):\penalty0 471--476, 2016.
|
||
|
||
\bibitem[Grefenstette et~al.(2015)Grefenstette, Hermann, Suleyman, and
|
||
Blunsom]{grefenstette2015learning}
|
||
Edward Grefenstette, Karl~Moritz Hermann, Mustafa Suleyman, and Phil Blunsom.
|
||
\newblock Learning to transduce with unbounded memory.
|
||
\newblock In \emph{Advances in Neural Information Processing Systems}, pages
|
||
1828--1836, 2015.
|
||
|
||
\bibitem[Griewank(1989)]{Griewank1989}
|
||
Andreas Griewank.
|
||
\newblock On automatic differentiation.
|
||
\newblock In M.~Iri and K.~Tanabe, editors, \emph{Mathematical Programming:
|
||
Recent Developments and Applications}, pages 83--108. Kluwer Academic
|
||
Publishers, 1989.
|
||
|
||
\bibitem[Griewank(2003)]{Griewank2003}
|
||
Andreas Griewank.
|
||
\newblock A mathematical view of automatic differentiation.
|
||
\newblock \emph{Acta Numerica}, 12:\penalty0 321--98, 2003.
|
||
\newblock \doi{10.1017/S0962492902000132}.
|
||
|
||
\bibitem[Griewank(2012)]{Griewank2012}
|
||
Andreas Griewank.
|
||
\newblock Who invented the reverse mode of differentiation?
|
||
\newblock \emph{Documenta Mathematica}, Extra Volume ISMP:\penalty0 389--400,
|
||
2012.
|
||
|
||
\bibitem[Griewank and Walther(2008)]{Griewank2008}
|
||
Andreas Griewank and Andrea Walther.
|
||
\newblock \emph{Evaluating Derivatives: Principles and Techniques of
|
||
Algorithmic Differentiation}.
|
||
\newblock Society for Industrial and Applied Mathematics, Philadelphia, 2008.
|
||
\newblock \doi{10.1137/1.9780898717761}.
|
||
|
||
\bibitem[Griewank et~al.(2012)Griewank, Kulshreshtha, and
|
||
Walther]{griewank2012numerical}
|
||
Andreas Griewank, Kshitij Kulshreshtha, and Andrea Walther.
|
||
\newblock On the numerical stability of algorithmic differentiation.
|
||
\newblock \emph{Computing}, 94\penalty0 (2-4):\penalty0 125--149, 2012.
|
||
|
||
\bibitem[Gruslys et~al.(2016)Gruslys, Munos, Danihelka, Lanctot, and
|
||
Graves]{gruslys2016memory}
|
||
Audrunas Gruslys, R{\'e}mi Munos, Ivo Danihelka, Marc Lanctot, and Alex Graves.
|
||
\newblock Memory-efficient backpropagation through time.
|
||
\newblock In \emph{Advances in Neural Information Processing Systems}, pages
|
||
4125--4133, 2016.
|
||
|
||
\bibitem[Gupta et~al.(2015)Gupta, Agrawal, Gopalakrishnan, and
|
||
Narayanan]{gupta2015deep}
|
||
Suyog Gupta, Ankur Agrawal, Kailash Gopalakrishnan, and Pritish Narayanan.
|
||
\newblock Deep learning with limited numerical precision.
|
||
\newblock In \emph{Proceedings of the 32nd International Conference on Machine
|
||
Learning (ICML-15)}, pages 1737--1746, 2015.
|
||
|
||
\bibitem[Haase et~al.(2002)Haase, Langer, Lindner, and
|
||
M{\"u}hlhuber]{haase2002optimal}
|
||
Gundolf Haase, Ulrich Langer, Ewald Lindner, and Wolfram M{\"u}hlhuber.
|
||
\newblock Optimal sizing of industrial structural mechanics problems using
|
||
{AD}.
|
||
\newblock In \emph{Automatic Differentiation of Algorithms}, pages 181--188.
|
||
Springer, 2002.
|
||
|
||
\bibitem[Hadjis et~al.(2015)Hadjis, Abuzaid, Zhang, and
|
||
R{\'e}]{hadjis2015caffe}
|
||
Stefan Hadjis, Firas Abuzaid, Ce~Zhang, and Christopher R{\'e}.
|
||
\newblock Caffe con troll: Shallow ideas to speed up deep learning.
|
||
\newblock In \emph{Proceedings of the Fourth Workshop on Data analytics in the
|
||
Cloud}, page~2. ACM, 2015.
|
||
|
||
\bibitem[Hamilton(1837)]{Hamilton1837}
|
||
William~Rowan Hamilton.
|
||
\newblock Theory of conjugate functions, or algebraic couples; with a
|
||
preliminary and elementary essay on algebra as the science of pure time.
|
||
\newblock \emph{Transactions of the Royal Irish Academy}, 17:\penalty0
|
||
293--422, 1837.
|
||
|
||
\bibitem[Hasco{\"e}t and Pascual(2013)]{Hascoet2013}
|
||
Laurent Hasco{\"e}t and Valérie Pascual.
|
||
\newblock The {Tapenade} automatic differentiation tool: principles, model, and
|
||
specification.
|
||
\newblock \emph{ACM Transactions on Mathematical Software}, 39\penalty0 (3),
|
||
2013.
|
||
\newblock \doi{10.1145/2450153.2450158}.
|
||
|
||
\bibitem[Hecht-Nielsen(1989)]{Hecht1989}
|
||
Robert Hecht-Nielsen.
|
||
\newblock Theory of the backpropagation neural network.
|
||
\newblock In \emph{International Joint Conference on Neural Networks, IJCNN
|
||
1989}, pages 593--605. IEEE, 1989.
|
||
|
||
\bibitem[Hinkins(1994)]{Hinkins1994}
|
||
Ruth~L. Hinkins.
|
||
\newblock Parallel computation of automatic differentiation applied to magnetic
|
||
field calculations.
|
||
\newblock Technical report, Lawrence Berkeley Lab., CA, 1994.
|
||
|
||
\bibitem[Hinton and Ghahramani(1997)]{hinton1997generative}
|
||
Geoffrey~E. Hinton and Zoubin Ghahramani.
|
||
\newblock Generative models for discovering sparse distributed representations.
|
||
\newblock \emph{Philosophical Transactions of the Royal Society of London B:
|
||
Biological Sciences}, 352\penalty0 (1358):\penalty0 1177--1190, 1997.
|
||
|
||
\bibitem[Hoffman and Gelman(2014)]{Hoffman2014}
|
||
Matthew~D. Hoffman and Andrew Gelman.
|
||
\newblock The no-{U}-turn sampler: Adaptively setting path lengths in
|
||
{H}amiltonian {M}onte {C}arlo.
|
||
\newblock \emph{Journal of Machine Learning Research}, 15:\penalty0 1351--1381,
|
||
2014.
|
||
|
||
\bibitem[Horn(1977)]{horn1977understanding}
|
||
Berthold K.~P. Horn.
|
||
\newblock Understanding image intensities.
|
||
\newblock \emph{Artificial Intelligence}, 8:\penalty0 201--231, 1977.
|
||
|
||
\bibitem[Horwedel et~al.(1988)Horwedel, Worley, Oblow, and Pin]{Horwedel1988}
|
||
Jim~E. Horwedel, Brian~A. Worley, E.~M. Oblow, and F.~G. Pin.
|
||
\newblock {GRESS} version 1.0 user's manual.
|
||
\newblock Technical Memorandum ORNL/TM 10835, Martin Marietta Energy Systems,
|
||
Inc., Oak Ridge National Laboratory, Oak Ridge, 1988.
|
||
|
||
\bibitem[Jerrell(1997)]{Jerrell1997}
|
||
Max~E. Jerrell.
|
||
\newblock Automatic differentiation and interval arithmetic for estimation of
|
||
disequilibrium models.
|
||
\newblock \emph{Computational Economics}, 10\penalty0 (3):\penalty0 295--316,
|
||
1997.
|
||
|
||
\bibitem[Jia et~al.(2014)Jia, Shelhamer, Donahue, Karayev, Long, Girshick,
|
||
Guadarrama, and Darrell]{jia2014caffe}
|
||
Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross
|
||
Girshick, Sergio Guadarrama, and Trevor Darrell.
|
||
\newblock Caffe: Convolutional architecture for fast feature embedding.
|
||
\newblock In \emph{Proceedings of the 22nd ACM International Conference on
|
||
Multimedia}, pages 675--678. ACM, 2014.
|
||
|
||
\bibitem[Johnson et~al.(2016)Johnson, Duvenaud, Wiltschko, Adams, and
|
||
Datta]{johnson2016composing}
|
||
Matthew Johnson, David~K Duvenaud, Alex Wiltschko, Ryan~P Adams, and Sandeep~R
|
||
Datta.
|
||
\newblock Composing graphical models with neural networks for structured
|
||
representations and fast inference.
|
||
\newblock In \emph{Advances in Neural Information Processing Systems}, pages
|
||
2946--2954, 2016.
|
||
|
||
\bibitem[Jones et~al.(1993{\natexlab{a}})Jones, Gomard, and
|
||
Sestoft]{jones1993partial}
|
||
Neil~D Jones, Carsten~K Gomard, and Peter Sestoft.
|
||
\newblock \emph{Partial evaluation and automatic program generation}.
|
||
\newblock Peter Sestoft, 1993{\natexlab{a}}.
|
||
|
||
\bibitem[Jones and Launchbury(1991)]{jones1991unboxed}
|
||
Simon L~Peyton Jones and John Launchbury.
|
||
\newblock Unboxed values as first class citizens in a non-strict functional
|
||
language.
|
||
\newblock In \emph{Conference on Functional Programming Languages and Computer
|
||
Architecture}, pages 636--666. Springer, 1991.
|
||
|
||
\bibitem[Jones et~al.(1993{\natexlab{b}})Jones, Hall, Hammond, Partain, and
|
||
Wadler]{jones1993glasgow}
|
||
SL~Peyton Jones, Cordy Hall, Kevin Hammond, Will Partain, and Philip Wadler.
|
||
\newblock The {G}lasgow {H}askell compiler: a technical overview.
|
||
\newblock In \emph{Proc. UK Joint Framework for Information Technology (JFIT)
|
||
Technical Conference}, volume~93, 1993{\natexlab{b}}.
|
||
|
||
\bibitem[Joulin and Mikolov(2015)]{joulin2015inferring}
|
||
Armand Joulin and Tomas Mikolov.
|
||
\newblock Inferring algorithmic patterns with stack-augmented recurrent nets.
|
||
\newblock In \emph{Advances in Neural Information Processing Systems}, pages
|
||
190--198, 2015.
|
||
|
||
\bibitem[Juedes(1991)]{Juedes1991}
|
||
David~W. Juedes.
|
||
\newblock A taxonomy of automatic differentiation tools.
|
||
\newblock In A.~Griewank and G.~F. Corliss, editors, \emph{Automatic
|
||
Differentiation of Algorithms: Theory, Implementation, and Application},
|
||
pages 315--29. Society for Industrial and Applied Mathematics, Philadelphia,
|
||
PA, 1991.
|
||
|
||
\bibitem[Kingma and Ba(2015)]{kingma2015adam}
|
||
D.~Kingma and J.~Ba.
|
||
\newblock Adam: A method for stochastic optimization.
|
||
\newblock In \emph{The International Conference on Learning Representations
|
||
(ICLR), San Diego}, 2015.
|
||
|
||
\bibitem[Kingma and Welling(2014)]{kingma2014auto}
|
||
Diederik~P. Kingma and Max Welling.
|
||
\newblock Auto-encoding variational {Bayes}.
|
||
\newblock In \emph{International Conference on Learning Representations}, 2014.
|
||
|
||
\bibitem[Krizhevsky et~al.(2012)Krizhevsky, Sutskever, and
|
||
Hinton]{krizhevsky2012imagenet}
|
||
Alex Krizhevsky, Ilya Sutskever, and Geoffrey~E. Hinton.
|
||
\newblock {ImageNet} classification with deep convolutional neural networks.
|
||
\newblock In \emph{Advances in Neural Information Processing Systems}, pages
|
||
1097--1105, 2012.
|
||
|
||
\bibitem[Kubo and Iri(1990)]{Kubo1990}
|
||
K.~Kubo and M.~Iri.
|
||
\newblock {PADRE2}, version 1---user's manual.
|
||
\newblock Research Memorandum RMI 90-01, Department of Mathematical Engineering
|
||
and Information Physics, University of Tokyo, Tokyo, 1990.
|
||
|
||
\bibitem[Kucukelbir et~al.(2017)Kucukelbir, Tran, Ranganath, Gelman, and
|
||
Blei]{kucukelbir2017automatic}
|
||
Alp Kucukelbir, Dustin Tran, Rajesh Ranganath, Andrew Gelman, and David~M.
|
||
Blei.
|
||
\newblock Automatic differentiation variational inference.
|
||
\newblock \emph{Journal of Machine Learning Research}, 18\penalty0
|
||
(14):\penalty0 1--45, 2017.
|
||
|
||
\bibitem[Kulkarni et~al.(2015)Kulkarni, Kohli, Tenenbaum, and
|
||
Mansinghka]{kulkarni2015picture}
|
||
Tejas~D. Kulkarni, Pushmeet Kohli, Joshua~B. Tenenbaum, and Vikash Mansinghka.
|
||
\newblock Picture: A probabilistic programming language for scene perception.
|
||
\newblock In \emph{The {IEEE} Conference on Computer Vision and Pattern
|
||
Recognition ({CVPR})}, June 2015.
|
||
|
||
\bibitem[Kumar et~al.(2016)Kumar, Irsoy, Ondruska, Iyyer, Bradbury, Gulrajani,
|
||
Zhong, Paulus, and Socher]{pmlr-v48-kumar16}
|
||
Ankit Kumar, Ozan Irsoy, Peter Ondruska, Mohit Iyyer, James Bradbury, Ishaan
|
||
Gulrajani, Victor Zhong, Romain Paulus, and Richard Socher.
|
||
\newblock Ask me anything: Dynamic memory networks for natural language
|
||
processing.
|
||
\newblock In Maria~Florina Balcan and Kilian~Q. Weinberger, editors,
|
||
\emph{Proceedings of The 33rd International Conference on Machine Learning},
|
||
volume~48 of \emph{Proceedings of Machine Learning Research}, pages
|
||
1378--1387, New York, New York, USA, 20--22 Jun 2016. PMLR.
|
||
|
||
\bibitem[Lawson(1971)]{Lawson1971}
|
||
C.~L. Lawson.
|
||
\newblock Computing derivatives using {W}-arithmetic and {U}-arithmetic.
|
||
\newblock Internal Computing Memorandum CM-286, Jet Propulsion Laboratory,
|
||
Pasadena, CA, 1971.
|
||
|
||
\bibitem[Le et~al.(2017)Le, Baydin, and Wood]{le2016inference}
|
||
Tuan~Anh Le, Atılım~Güneş Baydin, and Frank Wood.
|
||
\newblock Inference compilation and universal probabilistic programming.
|
||
\newblock In \emph{Proceedings of the 20th International Conference on
|
||
Artificial Intelligence and Statistics (AISTATS)}, volume~54 of
|
||
\emph{Proceedings of Machine Learning Research}, pages 1338--1348, Fort
|
||
Lauderdale, FL, USA, 2017. PMLR.
|
||
|
||
\bibitem[LeCun et~al.(1998)LeCun, Bottou, Bengio, and
|
||
Haffner]{lecun1998gradient}
|
||
Yann LeCun, L{\'e}on Bottou, Yoshua Bengio, and Patrick Haffner.
|
||
\newblock Gradient-based learning applied to document recognition.
|
||
\newblock \emph{Proceedings of the IEEE}, 86\penalty0 (11):\penalty0
|
||
2278--2324, 1998.
|
||
|
||
\bibitem[LeCun et~al.(2015)LeCun, Bengio, and Hinton]{lecun2015deep}
|
||
Yann LeCun, Yoshua Bengio, and Geoffrey Hinton.
|
||
\newblock Deep learning.
|
||
\newblock \emph{Nature}, 521\penalty0 (7553):\penalty0 436--444, 2015.
|
||
|
||
\bibitem[Leibniz(1685)]{Leibniz1685}
|
||
G.~W. Leibniz.
|
||
\newblock \emph{Machina arithmetica in qua non additio tantum et subtractio sed
|
||
et multiplicatio nullo, diviso vero paene nullo animi labore peragantur}.
|
||
\newblock Hannover, 1685.
|
||
|
||
\bibitem[Leroy(1997)]{leroy1997effectiveness}
|
||
Xavier Leroy.
|
||
\newblock The effectiveness of type-based unboxing.
|
||
\newblock In \emph{TIC 1997: Workshop Types in Compilation}, 1997.
|
||
|
||
\bibitem[Linnainmaa(1970)]{linnainmaa1970representation}
|
||
Seppo Linnainmaa.
|
||
\newblock The representation of the cumulative rounding error of an algorithm
|
||
as a taylor expansion of the local rounding errors.
|
||
\newblock Master's thesis, University of Helsinki, 1970.
|
||
|
||
\bibitem[Linnainmaa(1976)]{linnainmaa1976taylor}
|
||
Seppo Linnainmaa.
|
||
\newblock Taylor expansion of the accumulated rounding error.
|
||
\newblock \emph{{BIT} Numerical Mathematics}, 16\penalty0 (2):\penalty0
|
||
146--160, 1976.
|
||
|
||
\bibitem[Loper and Black(2014)]{loper2014opendr}
|
||
Matthew~M. Loper and Michael~J. Black.
|
||
\newblock {OpenDR}: An approximate differentiable renderer.
|
||
\newblock In \emph{European Conference on Computer Vision}, pages 154--169.
|
||
Springer, 2014.
|
||
|
||
\bibitem[Maclaurin(2016)]{maclaurin2016modeling}
|
||
Dougal Maclaurin.
|
||
\newblock \emph{Modeling, Inference and Optimization with Composable
|
||
Differentiable Procedures}.
|
||
\newblock PhD thesis, School of Engineering and Applied Sciences, Harvard
|
||
University, 2016.
|
||
|
||
\bibitem[Maclaurin et~al.(2015)Maclaurin, Duvenaud, and Adams]{Maclaurin2015}
|
||
Dougal Maclaurin, David Duvenaud, and Ryan Adams.
|
||
\newblock Gradient-based hyperparameter optimization through reversible
|
||
learning.
|
||
\newblock In \emph{International Conference on Machine Learning}, pages
|
||
2113--2122, 2015.
|
||
|
||
\bibitem[Manzyuk et~al.(2012)Manzyuk, Pearlmutter, Radul, Rush, and
|
||
Siskind]{manzyuk2012confusion}
|
||
Oleksandr Manzyuk, Barak~A. Pearlmutter, Alexey~Andreyevich Radul, David~R
|
||
Rush, and Jeffrey~Mark Siskind.
|
||
\newblock Confusion of tagged perturbations in forward automatic
|
||
differentiation of higher-order functions.
|
||
\newblock \emph{arXiv preprint arXiv:1211.4892}, 2012.
|
||
|
||
\bibitem[Mayne and Jacobson(1970)]{jacobson1970differential}
|
||
David~Q. Mayne and David~H. Jacobson.
|
||
\newblock \emph{Differential Dynamic Programming}.
|
||
\newblock American Elsevier Pub. Co., New York, 1970.
|
||
|
||
\bibitem[Mazourik(1991)]{Mazourik1991}
|
||
Vladimir Mazourik.
|
||
\newblock Integration of automatic differentiation into a numerical library for
|
||
{PC}'s.
|
||
\newblock In A.~Griewank and G.~F. Corliss, editors, \emph{Automatic
|
||
Differentiation of Algorithms: Theory, Implementation, and Application},
|
||
pages 315--29. Society for Industrial and Applied Mathematics, Philadelphia,
|
||
PA, 1991.
|
||
|
||
\bibitem[Meyer et~al.(2003)Meyer, Fournier, and Berg]{Meyer2003}
|
||
Renate Meyer, David~A. Fournier, and Andreas Berg.
|
||
\newblock Stochastic volatility: Bayesian computation using automatic
|
||
differentiation and the extended {Kalman} filter.
|
||
\newblock \emph{Econometrics Journal}, 6\penalty0 (2):\penalty0 408--420, 2003.
|
||
\newblock \doi{10.1111/1368-423X.t01-1-00116}.
|
||
|
||
\bibitem[Michelotti(1990)]{Michelotti1990}
|
||
L.~Michelotti.
|
||
\newblock {MXYZPTLK}: A practical, user-friendly {C++} implementation of
|
||
differential algebra: User's guide.
|
||
\newblock Technical Memorandum FN-535, Fermi National Accelerator Laboratory,
|
||
Batavia, IL, 1990.
|
||
|
||
\bibitem[Mikolov et~al.(2010)Mikolov, Karafi{\'a}t, Burget, {\v{C}}ernock{\`y},
|
||
and Khudanpur]{mikolov2010recurrent}
|
||
Tom{\'a}{\v{s}} Mikolov, Martin Karafi{\'a}t, Luk{\'a}{\v{s}} Burget, Jan
|
||
{\v{C}}ernock{\`y}, and Sanjeev Khudanpur.
|
||
\newblock Recurrent neural network based language model.
|
||
\newblock In \emph{Eleventh Annual Conference of the International Speech
|
||
Communication Association}, 2010.
|
||
|
||
\bibitem[Müller and Cusdin(2005)]{Muller2005}
|
||
J.~D. Müller and P.~Cusdin.
|
||
\newblock On the performance of discrete adjoint {CFD} codes using automatic
|
||
differentiation.
|
||
\newblock \emph{International Journal for Numerical Methods in Fluids},
|
||
47\penalty0 (8-9):\penalty0 939--945, 2005.
|
||
\newblock ISSN 1097-0363.
|
||
\newblock \doi{10.1002/fld.885}.
|
||
|
||
\bibitem[Naumann(2004)]{naumann2004optimal}
|
||
Uwe Naumann.
|
||
\newblock Optimal accumulation of {Jacobian} matrices by elimination methods on
|
||
the dual computational graph.
|
||
\newblock \emph{Mathematical Programming}, 99\penalty0 (3):\penalty0 399--421,
|
||
2004.
|
||
|
||
\bibitem[Naumann and Riehme(2005)]{Naumann2005}
|
||
Uwe Naumann and Jan Riehme.
|
||
\newblock Computing adjoints with the {NAGWare} {F}ortran~95 compiler.
|
||
\newblock In H.~M. B{\"u}cker, G.~Corliss, P.~Hovland, U.~Naumann, and
|
||
B.~Norris, editors, \emph{Automatic Differentiation: {A}pplications, Theory,
|
||
and Implementations}, Lecture Notes in Computational Science and Engineering,
|
||
pages 159--69. Springer, 2005.
|
||
|
||
\bibitem[Neal(1993)]{Neal1993}
|
||
Radford~M. Neal.
|
||
\newblock Probabilistic inference using {Markov} chain {Monte Carlo} methods.
|
||
\newblock Technical Report CRG-TR-93-1, Department of Computer Science,
|
||
University of Toronto, 1993.
|
||
|
||
\bibitem[Neidinger(1989)]{Neidinger1989}
|
||
Richard~D. Neidinger.
|
||
\newblock Automatic differentiation and {APL}.
|
||
\newblock \emph{College Mathematics Journal}, 20\penalty0 (3):\penalty0
|
||
238--51, 1989.
|
||
\newblock \doi{10.2307/2686776}.
|
||
|
||
\bibitem[Nolan(1953)]{Nolan1953}
|
||
John~F. Nolan.
|
||
\newblock Analytical differentiation on a digital computer.
|
||
\newblock Master's thesis, Massachusetts Institute of Technology, 1953.
|
||
|
||
\bibitem[Ostiguy and Michelotti(2007)]{Ostiguy2007}
|
||
J.~F. Ostiguy and L.~Michelotti.
|
||
\newblock Mxyzptlk: An efficient, native {C++} differentiation engine.
|
||
\newblock In \emph{Particle Accelerator Conference (PAC 2007)}, pages 3489--91.
|
||
IEEE, 2007.
|
||
\newblock \doi{10.1109/PAC.2007.4440468}.
|
||
|
||
\bibitem[Parker(1985)]{Parker1985}
|
||
David~B. Parker.
|
||
\newblock Learning-logic: Casting the cortex of the human brain in silicon.
|
||
\newblock Technical Report TR-47, Center for Computational Research in
|
||
Economics and Management Science, MIT, 1985.
|
||
|
||
\bibitem[Pascual and Hascoët(2008)]{Pascual2008}
|
||
Valérie Pascual and Laurent Hascoët.
|
||
\newblock {TAPENADE} for {C}.
|
||
\newblock In \emph{Advances in Automatic Differentiation}, Lecture Notes in
|
||
Computational Science and Engineering, pages 199--210. Springer, 2008.
|
||
\newblock \doi{10.1007/978-3-540-68942-3_18}.
|
||
|
||
\bibitem[Paszke et~al.(2017)Paszke, Gross, Chintala, Chanan, Yang, DeVito, Lin,
|
||
Desmaison, Antiga, and Lerer]{paszke2017automatic}
|
||
Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary
|
||
DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer.
|
||
\newblock Automatic differentiation in {PyTorch}.
|
||
\newblock In \emph{NIPS 2017 Autodiff Workshop: The Future of Gradient-based
|
||
Machine Learning Software and Techniques, Long Beach, CA, US, December 9,
|
||
2017}, 2017.
|
||
|
||
\bibitem[Pearlmutter(1994)]{Pearlmutter1994}
|
||
Barak~A. Pearlmutter.
|
||
\newblock Fast exact multiplication by the {Hessian}.
|
||
\newblock \emph{Neural Computation}, 6:\penalty0 147--60, 1994.
|
||
\newblock \doi{10.1162/neco.1994.6.1.147}.
|
||
|
||
\bibitem[Pearlmutter and Siskind(2008)]{pearlmutter2008reverse}
|
||
Barak~A. Pearlmutter and Jeffrey~Mark Siskind.
|
||
\newblock Reverse-mode {AD} in a functional framework: Lambda the ultimate
|
||
backpropagator.
|
||
\newblock \emph{ACM Transactions on Programming Languages and Systems
|
||
(TOPLAS)}, 30\penalty0 (2):\penalty0 1--36, March 2008.
|
||
\newblock \doi{10.1145/1330017.1330018}.
|
||
|
||
\bibitem[Peng and Robinson(1976)]{Peng1976}
|
||
Ding-Yu Peng and Donald~B. Robinson.
|
||
\newblock A new two-constant equation of state.
|
||
\newblock \emph{Industrial and Engineering Chemistry Fundamentals}, 15\penalty0
|
||
(1):\penalty0 59--64, 1976.
|
||
\newblock \doi{10.1021/i160057a011}.
|
||
|
||
\bibitem[Peterson(1989)]{peterson1989untagged}
|
||
John Peterson.
|
||
\newblock Untagged data in tagged environments: Choosing optimal
|
||
representations at compile time.
|
||
\newblock In \emph{Proceedings of the Fourth International Conference on
|
||
Functional Programming Languages and Computer Architecture}, pages 89--99.
|
||
ACM, 1989.
|
||
|
||
\bibitem[Pfeiffer(1987)]{Pfeiffer1987}
|
||
F.~W. Pfeiffer.
|
||
\newblock Automatic differentiation in {PROSE}.
|
||
\newblock \emph{SIGNUM Newsletter}, 22\penalty0 (1):\penalty0 2--8, 1987.
|
||
\newblock \doi{10.1145/24680.24681}.
|
||
|
||
\bibitem[Pock et~al.(2007)Pock, Pock, and Bischof]{Pock2007}
|
||
Thomas Pock, Michael Pock, and Horst Bischof.
|
||
\newblock Algorithmic differentiation: Application to variational problems in
|
||
computer vision.
|
||
\newblock \emph{IEEE Transactions on Pattern Analysis and Machine
|
||
Intelligence}, 29\penalty0 (7):\penalty0 1180--1193, 2007.
|
||
\newblock \doi{10.1109/TPAMI.2007.1044}.
|
||
|
||
\bibitem[Press et~al.(2007)Press, Teukolsky, Vetterling, and
|
||
Flannery]{Press2007}
|
||
William~H. Press, Saul~A. Teukolsky, William~T. Vetterling, and Brian~P.
|
||
Flannery.
|
||
\newblock \emph{Numerical Recipes: The Art of Scientific Computing}.
|
||
\newblock Cambridge University Press, 2007.
|
||
|
||
\bibitem[Rall(2006)]{Rall2006}
|
||
Louise~B. Rall.
|
||
\newblock Perspectives on automatic differentiation: Past, present, and future?
|
||
\newblock In M.~B\"{u}cker, G.~Corliss, U.~Naumann, P.~Hovland, and B.~Norris,
|
||
editors, \emph{Automatic Differentiation: Applications, Theory, and
|
||
Implementations}, volume~50 of \emph{Lecture Notes in Computational Science
|
||
and Engineering}, pages 1--14. Springer Berlin Heidelberg, 2006.
|
||
|
||
\bibitem[Rasmussen and Williams(2006)]{Rasmussen2006}
|
||
Carl~Edward Rasmussen and Christopher K.~I. Williams.
|
||
\newblock \emph{Gaussian processes for machine learning}.
|
||
\newblock {MIT} Press, 2006.
|
||
|
||
\bibitem[Revels et~al.(2016{\natexlab{a}})Revels, Lubin, and
|
||
Papamarkou]{RevelsLubinPapamarkou2016}
|
||
J.~Revels, M.~Lubin, and T.~Papamarkou.
|
||
\newblock Forward-mode automatic differentiation in {Julia}.
|
||
\newblock \emph{arXiv:1607.07892 [cs.MS]}, 2016{\natexlab{a}}.
|
||
\newblock URL \url{https://arxiv.org/abs/1607.07892}.
|
||
|
||
\bibitem[Revels et~al.(2016{\natexlab{b}})Revels, Lubin, and
|
||
Papamarkou]{revels2016forward}
|
||
Jarrett Revels, Miles Lubin, and Theodore Papamarkou.
|
||
\newblock Forward-mode automatic differentiation in {J}ulia.
|
||
\newblock \emph{arXiv preprint arXiv:1607.07892}, 2016{\natexlab{b}}.
|
||
|
||
\bibitem[Rezende et~al.(2014)Rezende, Mohamed, and
|
||
Wierstra]{rezende2014stochastic}
|
||
Danilo~Jimenez Rezende, Shakir Mohamed, and Daan Wierstra.
|
||
\newblock Stochastic backpropagation and approximate inference in deep
|
||
generative models.
|
||
\newblock In \emph{International Conference on Machine Learning}, pages
|
||
1278--1286, 2014.
|
||
|
||
\bibitem[Rich and Hill(1992)]{Hill1992}
|
||
Lawrence~C. Rich and David~R. Hill.
|
||
\newblock Automatic differentiation in {MATLAB}.
|
||
\newblock \emph{Applied Numerical Mathematics}, 9:\penalty0 33--43, 1992.
|
||
|
||
\bibitem[Ritchie et~al.(2016)Ritchie, Horsfall, and Goodman]{ritchie2016deep}
|
||
Daniel Ritchie, Paul Horsfall, and Noah~D Goodman.
|
||
\newblock Deep amortized inference for probabilistic programs.
|
||
\newblock \emph{arXiv preprint arXiv:1610.05735}, 2016.
|
||
|
||
\bibitem[Rollins(2009)]{Rollins2009}
|
||
Elizabeth Rollins.
|
||
\newblock Optimization of neural network feedback control systems using
|
||
automatic differentiation.
|
||
\newblock Master's thesis, Department of Aeronautics and Astronautics,
|
||
Massachusetts Institute of Technology, 2009.
|
||
|
||
\bibitem[Rozonoer(1959)]{Rozonoer-Pontryagin-1959a}
|
||
L.~I. Rozonoer.
|
||
\newblock {L}. {S}. {Pontryagin}'s maximum principle in the theory of optimum
|
||
systems---{Part} {II}.
|
||
\newblock \emph{Automat. i Telemekh.}, 20:\penalty0 1441--1458, 1959.
|
||
|
||
\bibitem[Rumelhart et~al.(1986)Rumelhart, Hinton, and
|
||
Williams]{rumelhart1986learning}
|
||
David~E. Rumelhart, Geoffrey~E. Hinton, and Ronald~J. Williams.
|
||
\newblock Learning representations by back-propagating errors.
|
||
\newblock \emph{Nature}, 323\penalty0 (6088):\penalty0 533, 1986.
|
||
|
||
\bibitem[Rump(1999)]{Rump1999}
|
||
Siegfried~M. Rump.
|
||
\newblock {INTLAB}---{INTerval} {LABoratory}.
|
||
\newblock In \emph{Developments in Reliable Computing}, pages 77--104. Kluwer
|
||
Academic Publishers, Dordrecht, 1999.
|
||
\newblock \doi{10.1007/978-94-017-1247-7_7}.
|
||
|
||
\bibitem[Salimans et~al.(2015)Salimans, Kingma, and Welling]{Salimans2014}
|
||
Tim Salimans, Diederik Kingma, and Max Welling.
|
||
\newblock Markov chain {Monte Carlo} and variational inference: Bridging the
|
||
gap.
|
||
\newblock In \emph{Proceedings of the 32nd International Conference on Machine
|
||
Learning (ICML-15)}, pages 1218--1226, 2015.
|
||
|
||
\bibitem[Salvatier et~al.(2016)Salvatier, Wiecki, and
|
||
Fonnesbeck]{salvatier2016probabilistic}
|
||
John Salvatier, Thomas~V Wiecki, and Christopher Fonnesbeck.
|
||
\newblock Probabilistic programming in {Python} using {PyMC3}.
|
||
\newblock \emph{PeerJ Computer Science}, 2:\penalty0 e55, 2016.
|
||
|
||
\bibitem[Schaul et~al.(2013)Schaul, Zhang, and LeCun]{schaul2013no}
|
||
Tom Schaul, Sixin Zhang, and Yann LeCun.
|
||
\newblock No more pesky learning rates.
|
||
\newblock In \emph{International Conference on Machine Learning}, pages
|
||
343--351, 2013.
|
||
|
||
\bibitem[Schmidhuber(2015)]{schmidhuber2015deep}
|
||
J{\"u}rgen Schmidhuber.
|
||
\newblock Deep learning in neural networks: An overview.
|
||
\newblock \emph{Neural Networks}, 61:\penalty0 85--117, 2015.
|
||
|
||
\bibitem[Schraudolph(1999)]{Schraudolph1999}
|
||
Nicol~N. Schraudolph.
|
||
\newblock Local gain adaptation in stochastic gradient descent.
|
||
\newblock In \emph{Proceedings of the International Conference on Artificial
|
||
Neural Networks}, pages 569--74, Edinburgh, Scotland, 1999. IEE London.
|
||
\newblock \doi{10.1049/cp:19991170}.
|
||
|
||
\bibitem[Schraudolph and Graepel(2003)]{Schraudolph2003}
|
||
Nicol~N. Schraudolph and Thore Graepel.
|
||
\newblock Combining conjugate direction methods with stochastic approximation
|
||
of gradients.
|
||
\newblock In \emph{Proceedings of the Ninth International Workshop on
|
||
Artificial Intelligence and Statistics}, 2003.
|
||
|
||
\bibitem[Seide and Agarwal(2016)]{seide2016cntk}
|
||
Frank Seide and Amit Agarwal.
|
||
\newblock {CNTK}: Microsoft's open-source deep-learning toolkit.
|
||
\newblock In \emph{Proceedings of the 22Nd ACM SIGKDD International Conference
|
||
on Knowledge Discovery and Data Mining}, KDD '16, pages 2135--2135, New York,
|
||
NY, USA, 2016. ACM.
|
||
\newblock ISBN 978-1-4503-4232-2.
|
||
\newblock \doi{10.1145/2939672.2945397}.
|
||
|
||
\bibitem[Shazeer et~al.(2017)Shazeer, Mirhoseini, Maziarz, Davis, Le, Hinton,
|
||
and Dean]{shazeer2017outrageously}
|
||
Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc Le,
|
||
Geoffrey Hinton, and Jeff Dean.
|
||
\newblock Outrageously large neural networks: The sparsely-gated
|
||
mixture-of-experts layer.
|
||
\newblock In \emph{International Conference on Learning Representations 2017},
|
||
2017.
|
||
|
||
\bibitem[Shivers(1991)]{shivers1991control}
|
||
Olin Shivers.
|
||
\newblock \emph{Control-flow analysis of higher-order languages}.
|
||
\newblock PhD thesis, Carnegie Mellon University, 1991.
|
||
|
||
\bibitem[Shtof et~al.(2013)Shtof, Agathos, Gingold, Shamir, and
|
||
{Cohen‐Or}]{Shtof2013}
|
||
Alex Shtof, Alexander Agathos, Yotam Gingold, Ariel Shamir, and Daniel
|
||
{Cohen‐Or}.
|
||
\newblock Geosemantic snapping for sketch-based modeling.
|
||
\newblock \emph{Computer Graphics Forum}, 32\penalty0 (2):\penalty0 245--53,
|
||
2013.
|
||
\newblock \doi{10.1111/cgf.12044}.
|
||
|
||
\bibitem[Siddharth et~al.(2017)Siddharth, Paige, van~de Meent, Desmaison,
|
||
Goodman, Kohli, Wood, and Torr]{siddharth2017learning}
|
||
N.~Siddharth, Brooks Paige, Jan-Willem van~de Meent, Alban Desmaison, Noah~D.
|
||
Goodman, Pushmeet Kohli, Frank Wood, and Philip Torr.
|
||
\newblock Learning disentangled representations with semi-supervised deep
|
||
generative models.
|
||
\newblock In I.~Guyon, U.~V. Luxburg, S.~Bengio, H.~Wallach, R.~Fergus,
|
||
S.~Vishwanathan, and R.~Garnett, editors, \emph{Advances in Neural
|
||
Information Processing Systems 30}, pages 5927--5937. Curran Associates,
|
||
Inc., 2017.
|
||
|
||
\bibitem[Simard et~al.(1998)Simard, {LeCun}, Denker, and Victorri]{Simard1998}
|
||
Patrice Simard, Yann {LeCun}, John Denker, and Bernard Victorri.
|
||
\newblock Transformation invariance in pattern recognition, tangent distance
|
||
and tangent propagation.
|
||
\newblock In G.~Orr and K.~Muller, editors, \emph{Neural Networks: Tricks of
|
||
the Trade}. Springer, 1998.
|
||
|
||
\bibitem[Sirkes and Tziperman(1997)]{sirkes-tziperman-1997a}
|
||
Z.~Sirkes and E.~Tziperman.
|
||
\newblock Finite difference of adjoint or adjoint of finite difference?
|
||
\newblock \emph{Monthly Weather Review}, 125\penalty0 (12):\penalty0 3373--8,
|
||
1997.
|
||
\newblock \doi{10.1175/1520-0493(1997)125<3373:FDOAOA>2.0.CO;2}.
|
||
|
||
\bibitem[Siskind and Pearlmutter(2005)]{SiskindPearlmutter2005a}
|
||
Jeffrey~Mark Siskind and Barak~A. Pearlmutter.
|
||
\newblock Perturbation confusion and referential transparency: Correct
|
||
functional implementation of forward-mode {AD}.
|
||
\newblock In Andrew Butterfield, editor, \emph{Implementation and Application
|
||
of Functional Languages---17th International Workshop, IFL'05}, pages 1--9,
|
||
Dublin, Ireland, 2005.
|
||
\newblock Trinity College Dublin Computer Science Department Technical Report
|
||
TCD-CS-2005-60.
|
||
|
||
\bibitem[Siskind and Pearlmutter(2008{\natexlab{a}})]{Siskind2008}
|
||
Jeffrey~Mark Siskind and Barak~A. Pearlmutter.
|
||
\newblock Using polyvariant union-free flow analysis to compile a higher-order
|
||
functional-programming language with a first-class derivative operator to
|
||
efficient {Fortran}-like code.
|
||
\newblock Technical Report TR-ECE-08-01, School of Electrical and Computer
|
||
Engineering, Purdue University, 2008{\natexlab{a}}.
|
||
|
||
\bibitem[Siskind and Pearlmutter(2008{\natexlab{b}})]{Siskind2008b}
|
||
Jeffrey~Mark Siskind and Barak~A. Pearlmutter.
|
||
\newblock Nesting forward-mode {AD} in a functional framework.
|
||
\newblock \emph{Higher-Order and Symbolic Computation}, 21\penalty0
|
||
(4):\penalty0 361--376, 2008{\natexlab{b}}.
|
||
|
||
\bibitem[Siskind and Pearlmutter(2016)]{siskind2016efficient}
|
||
Jeffrey~Mark Siskind and Barak~A. Pearlmutter.
|
||
\newblock Efficient implementation of a higher-order language with built-in
|
||
{AD}.
|
||
\newblock In \emph{7th International Conference on Algorithmic Differentiation,
|
||
Christ Church Oxford, UK, September 12--15, 2016}, 2016.
|
||
\newblock Also arXiv:1611.03416.
|
||
|
||
\bibitem[Siskind and Pearlmutter(2017)]{siskind2017divide}
|
||
Jeffrey~Mark Siskind and Barak~A. Pearlmutter.
|
||
\newblock Divide-and-conquer checkpointing for arbitrary programs with no user
|
||
annotation.
|
||
\newblock In \emph{NIPS 2017 Autodiff Workshop: The Future of Gradient-based
|
||
Machine Learning Software and Techniques, Long Beach, CA, US, December 9,
|
||
2017}, 2017.
|
||
\newblock Also arXiv:1708.06799.
|
||
|
||
\bibitem[Slusanschi and Dumitrel(2016)]{slusanschi2016adijac}
|
||
Emil~I. Slusanschi and Vlad Dumitrel.
|
||
\newblock {ADiJaC}---{A}utomatic differentiation of {J}ava classfiles.
|
||
\newblock \emph{ACM Transaction on Mathematical Software}, 43\penalty0
|
||
(2):\penalty0 9:1--9:33, September 2016.
|
||
\newblock ISSN 0098-3500.
|
||
\newblock \doi{10.1145/2904901}.
|
||
|
||
\bibitem[Speelpenning(1980)]{Speelpenning80}
|
||
Bert Speelpenning.
|
||
\newblock \emph{Compiling Fast Partial Derivatives of Functions Given by
|
||
Algorithms}.
|
||
\newblock PhD thesis, Department of Computer Science, University of Illinois at
|
||
Urbana-Champaign, 1980.
|
||
|
||
\bibitem[Sra et~al.(2011)Sra, Nowozin, and Wright]{Sra2011}
|
||
Suvrit Sra, Sebastian Nowozin, and Stephen~J. Wright.
|
||
\newblock \emph{Optimization for Machine Learning}.
|
||
\newblock {MIT} Press, 2011.
|
||
|
||
\bibitem[Srajer et~al.(2016)Srajer, Kukelova, and
|
||
Fitzgibbon]{srajer2016benchmark}
|
||
Filip Srajer, Zuzana Kukelova, and Andrew Fitzgibbon.
|
||
\newblock A benchmark of selected algorithmic differentiation tools on some
|
||
problems in machine learning and computer vision.
|
||
\newblock In \emph{AD2016: The 7th International Conference on Algorithmic
|
||
Differentiation, Monday 12th--Thursday 15th September 2016, Christ Church
|
||
Oxford, UK: Programme and Abstracts}, pages 181--184. Society for Industrial
|
||
and Applied Mathematics (SIAM), 2016.
|
||
|
||
\bibitem[Srinivasan and Todorov(2015)]{srinivasan-todorov-2015a}
|
||
Akshay Srinivasan and Emanuel Todorov.
|
||
\newblock Graphical {Newton}.
|
||
\newblock Technical Report arXiv:1508.00952, arXiv preprint, 2015.
|
||
|
||
\bibitem[Stuhlm{\"u}ller et~al.(2013)Stuhlm{\"u}ller, Taylor, and
|
||
Goodman]{stuhlmuller2013learning}
|
||
Andreas Stuhlm{\"u}ller, Jacob Taylor, and Noah Goodman.
|
||
\newblock Learning stochastic inverses.
|
||
\newblock In \emph{Advances in Neural Information Processing Systems}, pages
|
||
3048--3056, 2013.
|
||
|
||
\bibitem[Such et~al.(2017)Such, Madhavan, Conti, Lehman, Stanley, and
|
||
Clune]{such2017deep}
|
||
Felipe~Petroski Such, Vashisht Madhavan, Edoardo Conti, Joel Lehman, Kenneth~O.
|
||
Stanley, and Jeff Clune.
|
||
\newblock Deep neuroevolution: Genetic algorithms are a competitive alternative
|
||
for training deep neural networks for reinforcement learning.
|
||
\newblock \emph{arXiv preprint arXiv:1712.06567}, 2017.
|
||
|
||
\bibitem[Sukhbaatar et~al.(2015)Sukhbaatar, Weston, Fergus,
|
||
et~al.]{sukhbaatar2015end}
|
||
Sainbayar Sukhbaatar, Jason Weston, Rob Fergus, et~al.
|
||
\newblock End-to-end memory networks.
|
||
\newblock In \emph{Advances in Neural Information Processing Systems}, pages
|
||
2440--2448, 2015.
|
||
|
||
\bibitem[Sussman and Wisdom(2001)]{Sussman2001}
|
||
Gerald~J. Sussman and Jack Wisdom.
|
||
\newblock \emph{Structure and Interpretation of Classical Mechanics}.
|
||
\newblock {MIT} Press, 2001.
|
||
\newblock \doi{10.1063/1.1457268}.
|
||
|
||
\bibitem[Taylor et~al.(2014)Taylor, Stebbing, Ramakrishna, Keskin, Shotton,
|
||
Izadi, Hertzmann, and Fitzgibbon]{taylor2014user}
|
||
Jonathan Taylor, Richard Stebbing, Varun Ramakrishna, Cem Keskin, Jamie
|
||
Shotton, Shahram Izadi, Aaron Hertzmann, and Andrew Fitzgibbon.
|
||
\newblock User-specific hand modeling from monocular depth sequences.
|
||
\newblock In \emph{Proceedings of the {IEEE} Conference on Computer Vision and
|
||
Pattern Recognition}, pages 644--651, 2014.
|
||
|
||
\bibitem[Thomas et~al.(2006)Thomas, Dowell, and Hall]{thomas2006using}
|
||
Jeffrey~P. Thomas, Earl~H. Dowell, and Kenneth~C. Hall.
|
||
\newblock Using automatic differentiation to create a nonlinear reduced order
|
||
model of a computational fluid dynamic solver.
|
||
\newblock \emph{AIAA Paper}, 7115:\penalty0 2006, 2006.
|
||
|
||
\bibitem[Tieleman and Hinton(2012)]{tieleman2012lecture}
|
||
T.~Tieleman and G.~Hinton.
|
||
\newblock Lecture 6.5---{RMSProp}: Divide the gradient by a running average of
|
||
its recent magnitude.
|
||
\newblock \emph{COURSERA: Neural Networks for Machine Learning}, 4\penalty0
|
||
(2), 2012.
|
||
|
||
\bibitem[Tokui et~al.(2015)Tokui, Oono, Hido, and Clayton]{tokui2015chainer}
|
||
Seiya Tokui, Kenta Oono, Shohei Hido, and Justin Clayton.
|
||
\newblock Chainer: a next-generation open source framework for deep learning.
|
||
\newblock In \emph{Proceedings of Workshop on Machine Learning Systems
|
||
(LearningSys) in The Twenty-ninth Annual Conference on Neural Information
|
||
Processing Systems (NIPS)}, 2015.
|
||
|
||
\bibitem[Tran et~al.(2016)Tran, Kucukelbir, Dieng, Rudolph, Liang, and
|
||
Blei]{tran2016edward}
|
||
Dustin Tran, Alp Kucukelbir, Adji~B. Dieng, Maja Rudolph, Dawen Liang, and
|
||
David~M. Blei.
|
||
\newblock {Edward: A library for probabilistic modeling, inference, and
|
||
criticism}.
|
||
\newblock \emph{arXiv preprint arXiv:1610.09787}, 2016.
|
||
|
||
\bibitem[Tran et~al.(2017)Tran, Hoffman, Saurous, Brevdo, Murphy, and
|
||
Blei]{tran2017deep}
|
||
Dustin Tran, Matthew~D. Hoffman, Rif~A. Saurous, Eugene Brevdo, Kevin Murphy,
|
||
and David~M. Blei.
|
||
\newblock Deep probabilistic programming.
|
||
\newblock In \emph{International Conference on Learning Representations}, 2017.
|
||
|
||
\bibitem[Triggs et~al.(1999)Triggs, McLauchlan, Hartley, and
|
||
Fitzgibbon]{triggs1999bundle}
|
||
Bill Triggs, Philip~F. McLauchlan, Richard~I. Hartley, and Andrew~W.
|
||
Fitzgibbon.
|
||
\newblock Bundle adjustment—a modern synthesis.
|
||
\newblock In \emph{International Workshop on Vision Algorithms}, pages
|
||
298--372. Springer, 1999.
|
||
|
||
\bibitem[Tucker et~al.(2017)Tucker, Mnih, Maddison, Lawson, and
|
||
Sohl-Dickstein]{tucker2017rebar}
|
||
George Tucker, Andriy Mnih, Chris~J. Maddison, John Lawson, and Jascha
|
||
Sohl-Dickstein.
|
||
\newblock {REBAR}: Low-variance, unbiased gradient estimates for discrete
|
||
latent variable models.
|
||
\newblock In \emph{Advances in Neural Information Processing Systems}, pages
|
||
2624--2633, 2017.
|
||
|
||
\bibitem[{van Merri{\"e}nboer} et~al.(2017){van Merri{\"e}nboer}, Wiltschko,
|
||
and Moldovan]{van2017tangent}
|
||
Bart {van Merri{\"e}nboer}, Alexander~B. Wiltschko, and Dan Moldovan.
|
||
\newblock Tangent: Automatic differentiation using source code transformation
|
||
in {Python}.
|
||
\newblock \emph{arXiv preprint arXiv:1711.02712}, 2017.
|
||
|
||
\bibitem[Verma(2000)]{Verma2000}
|
||
Arun Verma.
|
||
\newblock An introduction to automatic differentiation.
|
||
\newblock \emph{Current Science}, 78\penalty0 (7):\penalty0 804--7, 2000.
|
||
|
||
\bibitem[Vishwanathan et~al.(2006)Vishwanathan, Schraudolph, Schmidt, and
|
||
Murphy]{Vishwanathan2006}
|
||
S.~V.~N. Vishwanathan, Nicol~N. Schraudolph, Mark~W. Schmidt, and Kevin~P.
|
||
Murphy.
|
||
\newblock Accelerated training of conditional random fields with stochastic
|
||
gradient methods.
|
||
\newblock In \emph{Proceedings of the 23rd International Conference on Machine
|
||
Learning (ICML '06)}, pages 969--76, 2006.
|
||
\newblock \doi{10.1145/1143844.1143966}.
|
||
|
||
\bibitem[Walther(2007)]{Walther2007}
|
||
Andrea Walther.
|
||
\newblock Automatic differentiation of explicit {Runge}-{Kutta} methods for
|
||
optimal control.
|
||
\newblock \emph{Computational Optimization and Applications}, 36\penalty0
|
||
(1):\penalty0 83--108, 2007.
|
||
\newblock \doi{10.1007/s10589-006-0397-3}.
|
||
|
||
\bibitem[Walther and Griewank(2012)]{Walther2012}
|
||
Andrea Walther and Andreas Griewank.
|
||
\newblock Getting started with {ADOL-C}.
|
||
\newblock In U.~Naumann and O.~Schenk, editors, \emph{Combinatorial Scientific
|
||
Computing}, chapter~7, pages 181--202. Chapman-Hall CRC Computational
|
||
Science, 2012.
|
||
\newblock \doi{10.1201/b11644-8}.
|
||
|
||
\bibitem[Wengert(1964)]{Wengert1964}
|
||
Robert~E. Wengert.
|
||
\newblock A simple automatic derivative evaluation program.
|
||
\newblock \emph{Communications of the {ACM}}, 7:\penalty0 463--4, 1964.
|
||
|
||
\bibitem[Werbos(1974)]{Werbos-1974a}
|
||
Paul~J. Werbos.
|
||
\newblock \emph{Beyond Regression: New Tools for Prediction and Analysis in the
|
||
Behavioral Sciences}.
|
||
\newblock PhD thesis, Harvard University, 1974.
|
||
|
||
\bibitem[Williams(1992)]{williams1992simple}
|
||
Ronald~J. Williams.
|
||
\newblock Simple statistical gradient-following algorithms for connectionist
|
||
reinforcement learning.
|
||
\newblock \emph{Machine Learning}, 8\penalty0 (3-4):\penalty0 229--256, 1992.
|
||
|
||
\bibitem[Willkomm and Vehreschild(2013)]{Willkomm2013}
|
||
J.~Willkomm and A.~Vehreschild.
|
||
\newblock The {ADiMat} handbook, 2013.
|
||
\newblock URL \url{http://adimat.sc.informatik.tu-darmstadt.de/doc/}.
|
||
|
||
\bibitem[Wingate et~al.(2011)Wingate, Goodman, Stuhlmüller, and
|
||
Siskind]{Wingate2011}
|
||
David Wingate, Noah Goodman, Andreas Stuhlmüller, and Jeffrey~Mark Siskind.
|
||
\newblock Nonstandard interpretations of probabilistic programs for efficient
|
||
inference.
|
||
\newblock \emph{Advances in Neural Information Processing Systems}, 23, 2011.
|
||
|
||
\bibitem[Yang et~al.(2008)Yang, Zhao, Yan, and Chen]{Yang2008}
|
||
Weiwei Yang, Yong Zhao, Li~Yan, and Xiaoqian Chen.
|
||
\newblock Application of {PID} controller based on {BP} neural network using
|
||
automatic differentiation method.
|
||
\newblock In F.~Sun, J.~Zhang, Y.~Tan, J.~Cao, and W.~Yu, editors,
|
||
\emph{Advances in Neural Networks---ISNN 2008}, volume 5264 of \emph{Lecture
|
||
Notes in Computer Science}, pages 702--711. Springer Berlin Heidelberg, 2008.
|
||
\newblock \doi{10.1007/978-3-540-87734-9_80}.
|
||
|
||
\bibitem[Yildirim et~al.(2015)Yildirim, Kulkarni, Freiwald, and
|
||
Tenenbaum]{yildirim2015efficient}
|
||
Ilker Yildirim, Tejas~D. Kulkarni, Winrich~A. Freiwald, and Joshua~B.
|
||
Tenenbaum.
|
||
\newblock Efficient and robust analysis-by-synthesis in vision: A computational
|
||
framework, behavioral tests, and modeling neuronal representations.
|
||
\newblock In \emph{Annual Conference of the Cognitive Science Society}, 2015.
|
||
|
||
\bibitem[Yu and Siskind(2013)]{Yu2013}
|
||
Haonan Yu and Jeffrey~Mark Siskind.
|
||
\newblock Grounded language learning from video described with sentences.
|
||
\newblock In \emph{Proceedings of the 51st Annual Meeting of the Association
|
||
for Computational Linguistics}, pages 53--63, Sofia, Bulgaria, 2013.
|
||
Association for Computational Linguistics.
|
||
|
||
\bibitem[Zaremba et~al.(2016)Zaremba, Mikolov, Joulin, and
|
||
Fergus]{zaremba2016learning}
|
||
Wojciech Zaremba, Tomas Mikolov, Armand Joulin, and Rob Fergus.
|
||
\newblock Learning simple algorithms from examples.
|
||
\newblock In \emph{International Conference on Machine Learning}, pages
|
||
421--429, 2016.
|
||
|
||
\bibitem[Zhu et~al.(1997)Zhu, Byrd, Lu, and Nocedal]{Zhu1997}
|
||
Ciyou Zhu, Richard~H. Byrd, Peihuang Lu, and Jorge Nocedal.
|
||
\newblock Algorithm 778: {L-BFGS-B}: {Fortran} subroutines for large-scale
|
||
bound-constrained optimization.
|
||
\newblock \emph{ACM Transactions on Mathematical Software (TOMS)}, 23\penalty0
|
||
(4):\penalty0 550--60, 1997.
|
||
\newblock \doi{10.1145/279232.279236}.
|
||
|
||
\end{thebibliography}
|