Two Polyak-Type Step Sizes for Mirror Descent

arXiv2210.01532MaRDI QIDQ6412866FDOQ6412866

Y. H. Li, Jun-Kai You

Publication date: 4 October 2022

Abstract: We propose two Polyak-type step sizes for mirror descent and prove their convergences for minimizing convex locally Lipschitz functions. Both step sizes, unlike the original Polyak step size, do not need the optimal value of the objective function.

This page was built for publication: Two Polyak-Type Step Sizes for Mirror Descent

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6412866)