The Randomized Block Coordinate Descent Method in the H\"older Smooth Setting
Abstract
This work provides the first convergence analysis for the Randomized Block Coordinate Descent method for minimizing a function that is both H\"older smooth and block H\"older smooth. Our analysis applies to objective functions that are non-convex, convex, and strongly convex. For non-convex functions, we show that the expected gradient norm reduces at an rate, where is the iteration count and is the H\"older exponent. For convex functions, we show that the expected suboptimality gap reduces at the rate . In the strongly convex setting, we show this rate for the expected suboptimality gap improves to when and to a linear rate when . Notably, these new convergence rates coincide with those furnished in the existing literature for the Lipschitz smooth setting.
Cite
@article{arxiv.2403.08080,
title = {The Randomized Block Coordinate Descent Method in the H\"older Smooth Setting},
author = {Leandro Farias Maia and David Huckleberry Gutman},
journal= {arXiv preprint arXiv:2403.08080},
year = {2024}
}