26 citations · 138 across the 24 of their papers we have counts for
5 papers · 1 filter
PMGT-VR: A decentralized proximal-gradient algorithmic framework with variance reduction
Haishan Ye, Wei Xiong, Tong Zhang
This paper considers the decentralized composite optimization problem. We propose a novel decentralized variance-reduction proximal-gradient algorithmic framework, called PMGT-VR,…
Error Compensated Distributed SGD Can Be Accelerated
Xun Qian, Peter Richtárik, Tong Zhang
Gradient compression is a recent and increasingly popular technique for reducing the communication cost in distributed training of large-scale machine learning models. In this work…
Mirror Natural Evolution Strategies
Haishan Ye, Tong Zhang
Evolution Strategies such as CMA-ES (covariance matrix adaptation evolution strategy) and NES (natural evolution strategy) have been widely used in machine learning applications, w…
A Stochastic Extra-Step Quasi-Newton Method for Nonsmooth Nonconvex Optimization
Minghan Yang, Andre Milzarek, Zaiwen Wen +1
In this paper, a novel stochastic extra-step quasi-Newton method is developed to solve a class of nonsmooth nonconvex composite optimization problems. We assume that the gradient o…
Improved Optimization of Finite Sums with Minibatch Stochastic Variance Reduced Proximal Iterations
Jialei Wang, Tong Zhang
We present novel minibatch stochastic optimization methods for empirical risk minimization problems, the methods efficiently leverage variance reduced first-order and sub-sampled h…