Saved in:
Bibliographic Details
Main Authors: Felzenszwalb, Pedro, Lee, Heon
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.00741
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910027539808256
author Felzenszwalb, Pedro
Lee, Heon
author_facet Felzenszwalb, Pedro
Lee, Heon
contents We consider the problem of maximizing a convex function over a closed convex set in a real Hilbert space. For linear functions, we show that a single orthogonal projection suffices to obtain an approximate solution. For continuous convex functions over convex sets, we show that projected subgradient ascent converges to a first-order stationary point when using arbitrarily large step sizes. Taking the step sizes to infinity leads to a deterministic variant of the conditional gradient algorithm, and iterated linear optimization as a special case.
format Preprint
id arxiv_https___arxiv_org_abs_2511_00741
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Projected Subgradient Ascent for Convex Maximization
Felzenszwalb, Pedro
Lee, Heon
Optimization and Control
Numerical Analysis
90C99
We consider the problem of maximizing a convex function over a closed convex set in a real Hilbert space. For linear functions, we show that a single orthogonal projection suffices to obtain an approximate solution. For continuous convex functions over convex sets, we show that projected subgradient ascent converges to a first-order stationary point when using arbitrarily large step sizes. Taking the step sizes to infinity leads to a deterministic variant of the conditional gradient algorithm, and iterated linear optimization as a special case.
title Projected Subgradient Ascent for Convex Maximization
topic Optimization and Control
Numerical Analysis
90C99
url https://arxiv.org/abs/2511.00741