English

Parameter-free version of Adaptive Gradient Methods for Strongly-Convex Functions

Machine Learning 2023-07-18 v2 Optimization and Control

Abstract

The optimal learning rate for adaptive gradient methods applied to {\lambda}-strongly convex functions relies on the parameters {\lambda} and learning rate {\eta}. In this paper, we adapt a universal algorithm along the lines of Metagrad, to get rid of this dependence on {\lambda} and {\eta}. The main idea is to concurrently run multiple experts and combine their predictions to a master algorithm. This master enjoys O(d log T) regret bounds.

Keywords

Cite

@article{arxiv.2306.06613,
  title  = {Parameter-free version of Adaptive Gradient Methods for Strongly-Convex Functions},
  author = {Deepak Gouda and Hassan Naveed and Salil Kamath},
  journal= {arXiv preprint arXiv:2306.06613},
  year   = {2023}
}
R2 v1 2026-06-28T11:02:12.079Z