activity
20172021
most citedMulti-Level Stochastic Gradient Methods for Nested Composition Optimization

5 citations · 13 across the 4 of their papers we have counts for

collaborators

6 papers

stat.ME2021

Pre-processing with Orthogonal Decompositions for High-dimensional Explanatory Variables

Xu Han, Ethan X Fang, Cheng Yong Tang

Strong correlations between explanatory variables are problematic for high-dimensional regularized regression methods. Due to the violation of the Irrepresentable Condition, the po…

stat.ML20204 cited

Nearly Dimension-Independent Sparse Linear Bandit over Small Action Spaces via Best Subset Selection

Yining Wang, Yi Chen, Ethan X. Fang +2

We consider the stochastic contextual bandit problem under the high dimensional linear model. We focus on the case where the action space is finite and random, with each action ass…

cs.LG2019

Inductive Bias of Gradient Descent based Adversarial Training on Separable Data

Yan Li, Ethan X. Fang, Huan Xu +1

Adversarial training is a principled approach for training robust neural networks. Despite of tremendous successes in practice, its theoretical properties still remain largely unex…

stat.ME2019

High-dimensional Interactions Detection with Sparse Principal Hessian Matrix

Cheng Yong Tang, Ethan X. Fang, Yuexiao Dong

In statistical learning framework with regressions, interactions are the contributions to the response variable from the products of the explanatory variables. In high-dimensional…

math.OC20185 cited

Multi-Level Stochastic Gradient Methods for Nested Composition Optimization

Shuoguang Yang, Mengdi Wang, Ethan X. Fang

Stochastic gradient methods are scalable for solving large-scale optimization problems that involve empirical expectations of loss functions. Existing results mainly apply to optim…

stat.ML20174 cited

Misspecified Nonconvex Statistical Optimization for Phase Retrieval

Zhuoran Yang, Lin F. Yang, Ethan X. Fang +3

Existing nonconvex statistical optimization theory and methods crucially rely on the correct specification of the underlying "true" statistical models. To address this issue, we ta…