The reviewed record of science sign in
Pith

arxiv: 1911.11271 · v6 · pith:TLQ7BKOG · submitted 2019-11-25 · math.OC

Adaptive Catalyst for Smooth Convex Optimization

Reviewed by Pithpith:TLQ7BKOGopen to challenge →

classification math.OC
keywords catalystadaptiveinneralgorithmalgorithmsallowsapproachconvex
0
0 comments X
read the original abstract

In this paper, we present a generic framework that allows accelerating almost arbitrary non-accelerated deterministic and randomized algorithms for smooth convex optimization problems. The main approach of our envelope is the same as in Catalyst (Lin et al., 2015): an accelerated proximal outer gradient method, which is used as an envelope for a non-accelerated inner method for the $\ell_2$ regularized auxiliary problem. Our algorithm has two key differences: 1) easily verifiable stopping criteria for inner algorithm; 2) the regularization parameter can be tunned along the way. As a result, the main contribution of our work is a new framework that applies to adaptive inner algorithms: Steepest Descent, Adaptive Coordinate Descent, Alternating Minimization. Moreover, in the non-adaptive case, our approach allows obtaining Catalyst without a logarithmic factor, which appears in the standard Catalyst (Lin et al., 2015, 2018).

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.