mhjensen
263 lines
14 KiB
HTML
263 lines
14 KiB
HTML
<!--
|
||
Automatically generated HTML file from DocOnce source
|
||
(https://github.com/hplgit/doconce/)
|
||
-->
|
||
<html>
|
||
<head>
|
||
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
|
||
<meta name="generator" content="DocOnce: https://github.com/hplgit/doconce/" />
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||
<meta name="description" content="Week 46: Support Vector Machines">
|
||
|
||
<title>Week 46: Support Vector Machines</title>
|
||
|
||
<!-- Bootstrap style: bootstrap -->
|
||
<link href="https://netdna.bootstrapcdn.com/bootstrap/3.1.1/css/bootstrap.min.css" rel="stylesheet">
|
||
<!-- not necessary
|
||
<link href="https://netdna.bootstrapcdn.com/font-awesome/4.0.3/css/font-awesome.css" rel="stylesheet">
|
||
-->
|
||
|
||
<style type="text/css">
|
||
|
||
/* Add scrollbar to dropdown menus in bootstrap navigation bar */
|
||
.dropdown-menu {
|
||
height: auto;
|
||
max-height: 400px;
|
||
overflow-x: hidden;
|
||
}
|
||
|
||
/* Adds an invisible element before each target to offset for the navigation
|
||
bar */
|
||
.anchor::before {
|
||
content:"";
|
||
display:block;
|
||
height:50px; /* fixed header height for style bootstrap */
|
||
margin:-50px 0 0; /* negative fixed header height */
|
||
}
|
||
</style>
|
||
|
||
|
||
</head>
|
||
|
||
<!-- tocinfo
|
||
{'highest level': 2,
|
||
'sections': [('Support Vector Machines, overarching aims', 2, None, '___sec0'),
|
||
('Hyperplanes and all that', 2, None, '___sec1'),
|
||
('What is a hyperplane?', 2, None, '___sec2'),
|
||
('A $p$-dimensional space of features', 2, None, '___sec3'),
|
||
('The two-dimensional case', 2, None, '___sec4'),
|
||
('Getting into the details', 2, None, '___sec5'),
|
||
('First attempt at a minimization approach', 2, None, '___sec6'),
|
||
('Solving the equations', 2, None, '___sec7'),
|
||
('Code Example', 2, None, '___sec8'),
|
||
('Problems with the Simpler Approach', 2, None, '___sec9'),
|
||
('A better approach', 2, None, '___sec10'),
|
||
('A quick Reminder on Lagrangian Multipliers',
|
||
2,
|
||
None,
|
||
'___sec11'),
|
||
('Adding the Multiplier', 2, None, '___sec12'),
|
||
('Setting up the Problem', 2, None, '___sec13'),
|
||
('The problem to solve', 2, None, '___sec14'),
|
||
('The last steps', 2, None, '___sec15'),
|
||
('A soft classifier', 2, None, '___sec16'),
|
||
('Soft optmization problem', 2, None, '___sec17'),
|
||
('Kernels and non-linearity', 2, None, '___sec18'),
|
||
('The equations', 2, None, '___sec19'),
|
||
('The problem to solve', 2, None, '___sec20'),
|
||
("Different kernels and Mercer's theorem", 2, None, '___sec21'),
|
||
('The moons example', 2, None, '___sec22'),
|
||
('Mathematical optimization of convex functions',
|
||
2,
|
||
None,
|
||
'___sec23'),
|
||
('How do we solve these problems?', 2, None, '___sec24'),
|
||
('A simple example', 2, None, '___sec25'),
|
||
('Back to the more realistic cases', 2, None, '___sec26')]}
|
||
end of tocinfo -->
|
||
|
||
<body>
|
||
|
||
|
||
|
||
<script type="text/x-mathjax-config">
|
||
MathJax.Hub.Config({
|
||
TeX: {
|
||
equationNumbers: { autoNumber: "none" },
|
||
extensions: ["AMSmath.js", "AMSsymbols.js", "autobold.js", "color.js"]
|
||
}
|
||
});
|
||
</script>
|
||
<script type="text/javascript" async
|
||
src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML">
|
||
</script>
|
||
|
||
|
||
|
||
|
||
<!-- Bootstrap navigation bar -->
|
||
<div class="navbar navbar-default navbar-fixed-top">
|
||
<div class="navbar-header">
|
||
<button type="button" class="navbar-toggle" data-toggle="collapse" data-target=".navbar-responsive-collapse">
|
||
<span class="icon-bar"></span>
|
||
<span class="icon-bar"></span>
|
||
<span class="icon-bar"></span>
|
||
</button>
|
||
<a class="navbar-brand" href="week46-bs.html">Week 46: Support Vector Machines</a>
|
||
</div>
|
||
|
||
<div class="navbar-collapse collapse navbar-responsive-collapse">
|
||
<ul class="nav navbar-nav navbar-right">
|
||
<li class="dropdown">
|
||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||
<ul class="dropdown-menu">
|
||
<!-- navigation toc: --> <li><a href="._week46-bs001.html#___sec0" style="font-size: 80%;">Support Vector Machines, overarching aims</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs002.html#___sec1" style="font-size: 80%;">Hyperplanes and all that</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs003.html#___sec2" style="font-size: 80%;">What is a hyperplane?</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs004.html#___sec3" style="font-size: 80%;">A \( p \)-dimensional space of features</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs005.html#___sec4" style="font-size: 80%;">The two-dimensional case</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs006.html#___sec5" style="font-size: 80%;">Getting into the details</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs007.html#___sec6" style="font-size: 80%;">First attempt at a minimization approach</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs008.html#___sec7" style="font-size: 80%;">Solving the equations</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs009.html#___sec8" style="font-size: 80%;">Code Example</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs010.html#___sec9" style="font-size: 80%;">Problems with the Simpler Approach</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs011.html#___sec10" style="font-size: 80%;">A better approach</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs012.html#___sec11" style="font-size: 80%;">A quick Reminder on Lagrangian Multipliers</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs013.html#___sec12" style="font-size: 80%;">Adding the Multiplier</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs014.html#___sec13" style="font-size: 80%;">Setting up the Problem</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs015.html#___sec14" style="font-size: 80%;">The problem to solve</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs016.html#___sec15" style="font-size: 80%;">The last steps</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs017.html#___sec16" style="font-size: 80%;">A soft classifier</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs018.html#___sec17" style="font-size: 80%;">Soft optmization problem</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs019.html#___sec18" style="font-size: 80%;">Kernels and non-linearity</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs020.html#___sec19" style="font-size: 80%;">The equations</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs021.html#___sec20" style="font-size: 80%;">The problem to solve</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs022.html#___sec21" style="font-size: 80%;">Different kernels and Mercer's theorem</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs023.html#___sec22" style="font-size: 80%;">The moons example</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs024.html#___sec23" style="font-size: 80%;">Mathematical optimization of convex functions</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs025.html#___sec24" style="font-size: 80%;">How do we solve these problems?</a></li>
|
||
<!-- navigation toc: --> <li><a href="#___sec25" style="font-size: 80%;">A simple example</a></li>
|
||
<!-- navigation toc: --> <li><a href="._week46-bs027.html#___sec26" style="font-size: 80%;">Back to the more realistic cases</a></li>
|
||
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</div>
|
||
</div>
|
||
</div> <!-- end of navigation bar -->
|
||
|
||
<div class="container">
|
||
|
||
<p> </p><p> </p><p> </p> <!-- add vertical space -->
|
||
|
||
<a name="part0026"></a>
|
||
<!-- !split -->
|
||
|
||
<h2 id="___sec25" class="anchor">A simple example </h2>
|
||
|
||
<p>
|
||
We remind ourselves about the general problem we want to solve
|
||
$$
|
||
\begin{align*}
|
||
&\mathrm{min}_{x}\hspace{0.2cm} \frac{1}{2}\boldsymbol{x}^T\boldsymbol{P}\boldsymbol{x}+\boldsymbol{q}^T\boldsymbol{x},\\ \nonumber
|
||
&\mathrm{subject\hspace{0.1cm} to} \hspace{0.2cm} \boldsymbol{G}\boldsymbol{x} \preceq \boldsymbol{h} \wedge \boldsymbol{A}\boldsymbol{x}=f.
|
||
\end{align*}
|
||
$$
|
||
|
||
<p>
|
||
Let us show how to perform the optmization using a simple case. Assume we want to optimize the following problem
|
||
$$
|
||
\begin{align*}
|
||
&\mathrm{min}_{x}\hspace{0.2cm} \frac{1}{2}x^2+5x+3y \\ \nonumber
|
||
&\mathrm{subject to} \\ \nonumber
|
||
&x, y \geq 0 \\ \nonumber
|
||
&x+3y \geq 15 \\ \nonumber
|
||
&2x+5y \leq 100 \\ \nonumber
|
||
&3x+4y \leq 80. \\ \nonumber
|
||
\end{align*}
|
||
$$
|
||
|
||
The minimization problem can be rewritten in terms of vectors and matrices as (with \( x \) and \( y \) being the unknowns)
|
||
$$
|
||
\frac{1}{2}\begin{bmatrix} x\\ y \end{bmatrix}^T \begin{bmatrix} 1 & 0\\ 0 & 0 \end{bmatrix} \begin{bmatrix} x \\ y \end{bmatrix} + \begin{bmatrix}3\\ 4 \end{bmatrix}^T \begin{bmatrix}x \\ y \end{bmatrix}.
|
||
$$
|
||
|
||
Similarly, we can now set up the inequalities (we need to change \( \geq \) to \( \leq \) by multiplying with \( -1 \) on bot sides) as the following matrix-vector equation
|
||
$$
|
||
\begin{bmatrix} -1 & 0 \\ 0 & -1 \\ -1 & -3 \\ 2 & 5 \\ 3 & 4\end{bmatrix}\begin{bmatrix} x \\ y\end{bmatrix} \preceq \begin{bmatrix}0 \\ 0\\ -15 \\ 100 \\ 80\end{bmatrix}.
|
||
$$
|
||
|
||
We have collapsed all the inequalities into a single matrix \( \boldsymbol{G} \). We see also that our matrix
|
||
$$
|
||
\boldsymbol{P} =\begin{bmatrix} 1 & 0\\ 0 & 0 \end{bmatrix}
|
||
$$
|
||
|
||
is clearly positive semi-definite (all eigenvalues larger or equal zero).
|
||
Finally, the vector \( \boldsymbol{h} \) is defined as
|
||
$$
|
||
\boldsymbol{h} = \begin{bmatrix}0 \\ 0\\ -15 \\ 100 \\ 80\end{bmatrix}.
|
||
$$
|
||
|
||
<p>
|
||
Since we don't have any equalities the matrix \( \boldsymbol{A} \) is set to zero
|
||
The following code solves the equations for us
|
||
<p>
|
||
|
||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #408080; font-style: italic"># Import the necessary packages</span>
|
||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">numpy</span>
|
||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">cvxopt</span> <span style="color: #008000; font-weight: bold">import</span> matrix
|
||
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">cvxopt</span> <span style="color: #008000; font-weight: bold">import</span> solvers
|
||
P <span style="color: #666666">=</span> matrix(numpy<span style="color: #666666">.</span>diag([<span style="color: #666666">1</span>,<span style="color: #666666">0</span>]), tc<span style="color: #666666">=</span>’d’)
|
||
q <span style="color: #666666">=</span> matrix(numpy<span style="color: #666666">.</span>array([<span style="color: #666666">3</span>,<span style="color: #666666">4</span>]), tc<span style="color: #666666">=</span>’d’)
|
||
G <span style="color: #666666">=</span> matrix(numpy<span style="color: #666666">.</span>array([[<span style="color: #666666">-1</span>,<span style="color: #666666">0</span>],[<span style="color: #666666">0</span>,<span style="color: #666666">-1</span>],[<span style="color: #666666">-1</span>,<span style="color: #666666">-3</span>],[<span style="color: #666666">2</span>,<span style="color: #666666">5</span>],[<span style="color: #666666">3</span>,<span style="color: #666666">4</span>]]), tc<span style="color: #666666">=</span>’d’)
|
||
h <span style="color: #666666">=</span> matrix(numpy<span style="color: #666666">.</span>array([<span style="color: #666666">0</span>,<span style="color: #666666">0</span>,<span style="color: #666666">-15</span>,<span style="color: #666666">100</span>,<span style="color: #666666">80</span>]), tc<span style="color: #666666">=</span>’d’)
|
||
<span style="color: #408080; font-style: italic"># Construct the QP, invoke solver</span>
|
||
sol <span style="color: #666666">=</span> solvers<span style="color: #666666">.</span>qp(P,q,G,h)
|
||
<span style="color: #408080; font-style: italic"># Extract optimal value and solution</span>
|
||
sol[’x’]
|
||
sol[’primal objective’]
|
||
</pre></div>
|
||
<p>
|
||
<p>
|
||
<!-- navigation buttons at the bottom of the page -->
|
||
<ul class="pagination">
|
||
<li><a href="._week46-bs025.html">«</a></li>
|
||
<li><a href="._week46-bs000.html">1</a></li>
|
||
<li><a href="">...</a></li>
|
||
<li><a href="._week46-bs018.html">19</a></li>
|
||
<li><a href="._week46-bs019.html">20</a></li>
|
||
<li><a href="._week46-bs020.html">21</a></li>
|
||
<li><a href="._week46-bs021.html">22</a></li>
|
||
<li><a href="._week46-bs022.html">23</a></li>
|
||
<li><a href="._week46-bs023.html">24</a></li>
|
||
<li><a href="._week46-bs024.html">25</a></li>
|
||
<li><a href="._week46-bs025.html">26</a></li>
|
||
<li class="active"><a href="._week46-bs026.html">27</a></li>
|
||
<li><a href="._week46-bs027.html">28</a></li>
|
||
<li><a href="._week46-bs027.html">»</a></li>
|
||
</ul>
|
||
<!-- ------------------- end of main content --------------- -->
|
||
|
||
</div> <!-- end container -->
|
||
<!-- include javascript, jQuery *first* -->
|
||
<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.10.2/jquery.min.js"></script>
|
||
<script src="https://netdna.bootstrapcdn.com/bootstrap/3.0.0/js/bootstrap.min.js"></script>
|
||
|
||
<!-- Bootstrap footer
|
||
<footer>
|
||
<a href="http://..."><img width="250" align=right src="http://..."></a>
|
||
</footer>
|
||
-->
|
||
|
||
|
||
<center style="font-size:80%">
|
||
<!-- copyright only on the titlepage -->
|
||
</center>
|
||
|
||
|
||
</body>
|
||
</html>
|
||
|
||
|