资源分类
》 资源 》论文》Gradient Projection Iterative Sketch for Large-Scale Constrained Least-Squares

Gradient Projection Iterative Sketch for Large-Scale Constrained Least-Squares

2020-03-10 | |  68 |   35 |   0

Abstract

We propose a randomized first order optimization algorithm Gradient Projection Iterative Sketch (GPIS) and an accelerated variant for efficiently solving large scale constrained Least Squares (LS). We provide the first theoretical convergence analysis for both algorithms. An efficient implementation using a tailored linesearch scheme is also proposed. We demonstrate our methods’ computational efficiency compared to the classical accelerated gradient method, and the variance-reduced stochastic gradient methods through numerical experiments in various large synthetic/real data sets.

上一篇：Learning in POMDPs with Monte Carlo Tree Search

下一篇：Approximate Steepest Coordinate Descent

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...