资源分类
》 资源 》论文》Solving Ridge Regression using Sketched Preconditioned SVRG

Solving Ridge Regression using Sketched Preconditioned SVRG

2020-03-05 | |  72 |   52 |   0

Abstract

We develop a novel preconditioning method for ridge regression, based on recent linear sketching methods. By equipping Stochastic Variance Reduced Gradient (SVRG) with this preconditioning process, we obtain a significant speed-up relative to fast stochastic methods such as SVRG, SDCA and SAG.

上一篇：Interacting Particle Markov Chain Monte Carlo

下一篇：Softened Approximate Policy Iteration for Markov Games

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...