BriefGPT.xyz
Jun, 2015
非正则化:经验风险最小化的近端点近似和更快的随机算法
Un-regularizing: approximate proximal point and faster stochastic algorithms for empirical risk minimization
HTML
PDF
Roy Frostig, Rong Ge, Sham M. Kakade, Aaron Sidford
TL;DR
本文提出了一种新的随机算法,通过将强凸函数的最小化转化为函数规则化的逼近最小化,从而优化了经验风险最小化过程中的性能,实践表明该算法具有稳定性和行之有效的优势
Abstract
We develop a family of accelerated
stochastic algorithms
that minimize sums of
convex functions
. Our algorithms improve upon the fastest running time for
→