资源分类
》 资源 》论文》A Universally Optimal Multistage Accelerated Stochastic Gradient Method

A Universally Optimal Multistage Accelerated Stochastic Gradient Method

2020-02-21 | |  39 |   45 |   0

Abstract

We study the problem of minimizing a strongly convex, smooth function when we have noisy estimates of its gradient. We propose a novel multistage accelerated algorithm that is universally optimal in the sense that it achieves the optimal rate both in the deterministic and stochastic case and operates without knowledge of noise characteristics. The algorithm consists of stages that use a stochastic version of Nesterov’s method with a specific restart and parameters selected to achieve the fastest reduction in the bias-variance terms in the convergence rate bounds.

上一篇：Robust Principal Component Analysis with Adaptive Neighbors

下一篇：Re-examination of the Role of Latent Variables in Sequence Modeling

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...