资源分类
》 资源 》论文》Better Mini-Batch Algorithms via Accelerated Gradient Methods

Better Mini-Batch Algorithms via Accelerated Gradient Methods

2020-01-08 | |  60 |   42 |   0

Abstract

Mini-batch algorithms have been proposed as a way to speed-up stochastic convex optimization problems. We study how such algorithms can be improved using accelerated gradient methods. We provide a novel analysis, which shows how standard gradient methods may sometimes be insu?cient to obtain a significant speed-up and propose a novel accelerated gradient algorithm, which deals with this deficiency, enjoys a uniformly superior guarantee and works well in practice.

上一篇：Infinite Latent SVM for Classification and Multi-task Learning

下一篇：Noise Thresholds for Spectral Clustering

用户评价
全部评价

热门资源

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to learn...

    The move from hand-designed features to learned...

  • A Mathematical Mo...

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

  • Learning to Predi...

    Much of model-based reinforcement learning invo...