Optimal Computational Trade-Off of Inexact Proximal Methods
published: Jan. 16, 2013, recorded: December 2012, views: 2681
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
In this paper, we investigate the trade-off between convergence rate and computational cost when minimizing a composite functional with proximal-gradient methods, which are popular optimisation tools in machine learning. We consider the case when the proximity operator is approximated via an iterative procedure, which yields algorithms with two nested loops. We show that the strategy minimizing the computational cost to reach a desired accuracy in finite time is to keep the number of inner iterations constant, which differs from the strategy indicated by a convergence rate analysis.
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !