BriefGPT.xyz
Jan, 2019
随机复合优化的估计序列：方差降低、加速和对噪声的鲁棒性
Estimate Sequences for Stochastic Composite Optimization: Variance Reduction, Acceleration, and Robustness to Noise
HTML
PDF
Andrei Kulunchakov, Julien Mairal
TL;DR
本文提出了一种新的基于梯度的随机凸复合优化方法，将估计序列概念推广到随机优化算法中，以一种简单通用的方式证明了众多随机优化算法的收敛性，并提出几种可靠性策略。
Abstract
In this paper, we propose a unified view of gradient-based algorithms for
stochastic convex composite optimization
. By extending the concept of
estimate sequence
introduced by Nesterov, we interpret a large class
→