← Search

Nick Harvey

2 accepted papers

2023

Searching for Optimal Per-Coordinate Step-sizes with Multidimensional Backtracking

NeurIPS 2023poster

The backtracking line-search is an effective technique to automatically tune the step-size in smooth optimization. It guarantees similar performance to using the theoretically optimal step-size. Many approaches have been developed to instead tune per-coordinate step-sizes, also known as diagonal pre…

2020

Online mirror descent and dual averaging: keeping pace in the dynamic case

ICML 2020poster

Online mirror descent (OMD) and dual averaging (DA)—two fundamental algorithms for online convex optimization—are known to have very similar (and sometimes identical) performance guarantees when used with a fixed learning rate. Under dynamic learning rates, however, OMD is provably inferior to DA an…

Cited by 38SourcePDFScholar