From 02cee9a031576cee8487c3b83d868efc9cc13b33 Mon Sep 17 00:00:00 2001 From: Ilya Kulakov Date: Fri, 29 Mar 2019 15:30:18 -0700 Subject: [PATCH] Show what w^k - w^\star is a sum of eigenvectors of A multiplied by a scalar. Makes it easier to recognize meaning of the last component where it's not immediately obvious that x_i is a scalar but q_i is a vector. --- public/index.html | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/public/index.html b/public/index.html index e047563..086a603 100644 --- a/public/index.html +++ b/public/index.html @@ -351,7 +351,7 @@

First Steps: Gradient Descent

Moving back to our original space w, we can see that - w^k - w^\star = Qx^k=\sum_i^n x^0_i(1-\alpha\lambda_i)^k q_i + w^k - w^\star = Qx^k = \sum_i^n x^k_i q_i = \sum_i^n x^0_i(1-\alpha\lambda_i)^k q_i and there we have it -- gradient descent in closed form.