UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization

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.


Publié dans:
[Proceedings of NEURips 2019]
Présenté à:
NeurIPS 2019 : Thirty-third Conference on Neural Information Processing Systems, Vancouver, Canada, December 8-14, 2019
Année
2019
Mots-clefs:
Laboratoires:


Note: Le statut de ce fichier est: Anyone


 Notice créée le 2019-09-17, modifiée le 2020-04-20

Final:
Télécharger le document
PDF

Évaluer ce document:

Rate this document:
1
2
3
 
(Pas encore évalué)