Home Page

Papers

Submissions

News

Editorial Board

Special Issues

Open Source Software

Proceedings (PMLR)

Data (DMLR)

Transactions (TMLR)

Search

Statistics

Login

Frequently Asked Questions

Contact Us



RSS Feed

A Line-Search Descent Algorithm for Strict Saddle Functions with Complexity Guarantees

Michael J. O'Neill, Stephen J. Wright; 24(10):1−34, 2023.

Abstract

We describe a line-search algorithm which achieves the best-known worst-case complexity results for problems with a certain “strict saddle” property that has been observed to hold in low-rank matrix optimization problems. Our algorithm is adaptive, in the sense that it makes use of backtracking line searches and does not require prior knowledge of the parameters that define the strict saddle property.

[abs][pdf][bib]       
© JMLR 2023. (edit, beta)

Mastodon