资源分类
》 资源 》论文》Accelerated Mini-Batch Stochastic Dual Coordinate Ascent

Accelerated Mini-Batch Stochastic Dual Coordinate Ascent

2020-01-16 | |  64 |   40 |   0

Abstract

Stochastic dual coordinate ascent (SDCA) is an effective technique for solving regularized loss minimization problems in machine learning. This paper considers an extension of SDCA under the mini-batch setting that is often used in practice. Our main contribution is to introduce an accelerated mini-batch version of SDCA and prove a fast convergence rate for this method. We discuss an implementation of our method over a parallel computing system, and compare the results to both the vanilla stochastic dual coordinate ascent and to the accelerated deterministic gradient descent method of Nesterov [2007].

上一篇：Non-Linear Domain Adaptation with Boosting

下一篇：Adaptivity to Local Smoothness and Dimension in Kernel Regression

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • 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...