RECAPP: Crafting a More Efficient Catalyst for Convex Optimization

arXiv2206.08627MaRDI QIDQ6402347

Author name not available (Why is that?)

Publication date: 17 June 2022

Abstract: The accelerated proximal point algorithm (APPA), also known as "Catalyst", is a well-established reduction from convex optimization to approximate proximal point computation (i.e., regularized minimization). This reduction is conceptually elegant and yields strong convergence rate guarantees. However, these rates feature an extraneous logarithmic term arising from the need to compute each proximal point to high accuracy. In this work, we propose a novel Relaxed Error Criterion for Accelerated Proximal Point (RECAPP) that eliminates the need for high accuracy subproblem solutions. We apply RECAPP to two canonical problems: finite-sum and max-structured minimization. For finite-sum problems, we match the best known complexity, previously obtained by carefully-designed problem-specific algorithms. For minimizing $ma{x}_{y}f(x,y)$ where $f$ is convex in $x$ and strongly-concave in $y$, we improve on the best known (Catalyst-based) bound by a logarithmic factor.

Has companion code repository: https://github.com/yaircarmon/recapp

This page was built for publication: RECAPP: Crafting a More Efficient Catalyst for Convex Optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6402347)