Saved in:
Bibliographic Details
Main Authors: Lezane, Clement, Langer, Sophie, Koolen, Wouter M
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.18976
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915144983904256
author Lezane, Clement
Langer, Sophie
Koolen, Wouter M
author_facet Lezane, Clement
Langer, Sophie
Koolen, Wouter M
contents Acceleration for non-convex functions is a fundamental challenge in optimisation. We revisit star-convex functions, which are strictly unimodal on all lines through a minimizer. [1] accelerate unconstrained star-convex minimization of functions that are smooth with respect to the Euclidean norm. To do so, they add a certain binary search step to gradient descent. In this paper, we accelerate unconstrained star-convex minimization of functions that are weakly smooth with respect to an arbitrary norm. We add a binary search step to mirror descent, generalize the approach and refine its complexity analysis. We prove that our algorithms have sharp convergence rates for star-convex functions with $α$-Holder continuous gradients and demonstrate that our rates are nearly optimal for $p$-norms. [1] Near-Optimal Methods for Minimizing Star-Convex Functions and Beyond, Hinder Oliver and Sidford Aaron and Sohoni Nimit
format Preprint
id arxiv_https___arxiv_org_abs_2405_18976
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Accelerated Mirror Descent for Non-Euclidean Star-convex Functions
Lezane, Clement
Langer, Sophie
Koolen, Wouter M
Optimization and Control
Acceleration for non-convex functions is a fundamental challenge in optimisation. We revisit star-convex functions, which are strictly unimodal on all lines through a minimizer. [1] accelerate unconstrained star-convex minimization of functions that are smooth with respect to the Euclidean norm. To do so, they add a certain binary search step to gradient descent. In this paper, we accelerate unconstrained star-convex minimization of functions that are weakly smooth with respect to an arbitrary norm. We add a binary search step to mirror descent, generalize the approach and refine its complexity analysis. We prove that our algorithms have sharp convergence rates for star-convex functions with $α$-Holder continuous gradients and demonstrate that our rates are nearly optimal for $p$-norms. [1] Near-Optimal Methods for Minimizing Star-Convex Functions and Beyond, Hinder Oliver and Sidford Aaron and Sohoni Nimit
title Accelerated Mirror Descent for Non-Euclidean Star-convex Functions
topic Optimization and Control
url https://arxiv.org/abs/2405.18976