UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization
Lists
Only you see this
Abstract
We propose a novel adaptive, accelerated algorithm for the stochastic constrained convex optimization setting. Our method, which is inspired by the Mirror-Prox method, \emph{simultaneously} achieves the optimal rates for smooth/non-smooth problems with either deterministic/stochastic first-order oracles. This is done without any prior knowledge of the smoothness nor the noise properties of the problem. To the best of our knowledge, this is the first adaptive, unified algorithm that achieves the optimal rates in the constrained setting. We demonstrate the practical performance of our framework through extensive numerical experiments.
BibTeX
@inproceedings{kavis2019unixgrad,
author = {Ali Kavis and Kfir Y. Levy and Francis R. Bach and Volkan Cevher},
title = {{UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization}},
booktitle = {Advances in Neural Information Processing Systems},
year = {2019},
url = {https://openreview.net/forum?id=4TE5lvMcFoY},
}Loading related content...