From 9950370561a5a56765fc34ee504cefcbe8f382ee Mon Sep 17 00:00:00 2001
From: Morten Hjorth-Jensen <morten.hjorth-jensen@fys.uio.no>
Date: Mon, 31 Oct 2022 15:27:58 +0100
Subject: [PATCH] Create rmsprop.py

---
 doc/src/week39/rmsprop.py | 58 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 58 insertions(+)
 create mode 100644 doc/src/week39/rmsprop.py

diff --git a/doc/src/week39/rmsprop.py b/doc/src/week39/rmsprop.py
new file mode 100644
index 000000000..66e01e257
--- /dev/null
+++ b/doc/src/week39/rmsprop.py
@@ -0,0 +1,58 @@
+# Using Autograd to calculate gradients using RMSprop  and Stochastic Gradient descent
+# OLS example
+from random import random, seed
+import numpy as np
+import autograd.numpy as np
+import matplotlib.pyplot as plt
+from autograd import grad
+
+# Note change from previous example
+def CostOLS(y,X,theta):
+    return np.sum((y-X @ theta)**2)
+
+n = 10000
+x = np.random.rand(n,1)
+y = 2.0+3*x +4*x*x# +np.random.randn(n,1)
+
+X = np.c_[np.ones((n,1)), x, x*x]
+XT_X = X.T @ X
+theta_linreg = np.linalg.pinv(XT_X) @ (X.T @ y)
+print("Own inversion")
+print(theta_linreg)
+
+
+# Note that we request the derivative wrt third argument (theta, 2 here)
+training_gradient = grad(CostOLS,2)
+# Define parameters for Stochastic Gradient Descent
+n_epochs = 50
+M = 5   #size of each minibatch
+m = int(n/M) #number of minibatches
+# Guess for unknown parameters theta
+theta = np.random.randn(3,1)
+
+# Value for learning rate
+eta = 0.01
+# Value for parameter rho
+rho = 0.99
+# Including AdaGrad parameter to avoid possible division by zero
+delta  = 1e-8
+for epoch in range(n_epochs):
+    Giter = np.zeros(shape=(3,3))
+    for i in range(m):
+        random_index = M*np.random.randint(m)
+        xi = X[random_index:random_index+M]
+        yi = y[random_index:random_index+M]
+        gradients = (1.0/M)*training_gradient(yi, xi, theta)
+	# Previous value for the outer product of gradients
+        Previous = Giter
+	# Accumulated gradient
+#        Giter +=gradients @ gradients.T
+	# Scaling with rho the new and the previous results
+        Giter = (rho*Giter+(1-rho)*gradients*gradients)
+	# Taking the diagonal only and inverting
+        Ginverse = np.c_[eta/(delta+np.sqrt(np.diagonal(Giter)))]
+	# Hadamard product
+        update = np.multiply(Ginverse,gradients)
+        theta -= update
+print("theta from own RMSprop")
+print(theta)