1.2k citations · 1.7k across the 60 of their papers we have counts for
65 papers
Correcting Auto-Differentiation in Neural-ODE Training
Yewei Xu, Shi Chen, Qin Li
Does the use of auto-differentiation yield reasonable updates for deep neural networks (DNNs)? Specifically, when DNNs are designed to adhere to neural ODE architectures, can we tr…
Differentially Private Optimization for Smooth Nonconvex ERM
Changyu Gao, Stephen J. Wright
We develop simple differentially private optimization algorithms that move along directions of (expected) descent to find an approximate second-order solution for nonconvex ERM. We…
Cyclic Block Coordinate Descent With Variance Reduction for Composite Nonconvex Optimization
Xufeng Cai, Chaobing Song, Stephen J. Wright +1
Nonconvex optimization is central in solving many machine learning problems, in which block-wise structure is commonly encountered. In this work, we propose cyclic block coordinate…
On the Complexity of a Practical Primal-Dual Coordinate Method
Ahmet Alacaoglu, Volkan Cevher, Stephen J. Wright
We prove complexity bounds for the primal-dual algorithm with random extrapolation and coordinate descent (PURE-CD), which has been shown to obtain good practical performance for s…
A reduced order Schwarz method for nonlinear multiscale elliptic equations based on two-layer neural networks
Shi Chen, Zhiyan Ding, Qin Li +1
Neural networks are powerful tools for approximating high dimensional data that have been used in many contexts, including solution of partial differential equations (PDEs). We des…
Coordinate Linear Variance Reduction for Generalized Linear Programming
Chaobing Song, Cheuk Yin Lin, Stephen J. Wright +1
We study a class of generalized linear programs (GLP) in a large-scale setting, which includes simple, possibly nonsmooth convex regularizer and simple convex set constraints. By r…