activity
20192021
most citedZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization

34 citations · 70 across the 5 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2021

Toward Communication Efficient Adaptive Gradient Method

Xiangyi Chen, Xiaoyun Li, Ping Li

In recent years, distributed optimization is proven to be an effective approach to accelerate training of large scale machine learning models such as deep neural networks. With the…

cs.LG20215 cited

On the Convergence of Decentralized Adaptive Gradient Methods

Xiangyi Chen, Belhal Karimi, Weijie Zhao +1

Adaptive gradient methods including Adam, AdaGrad, and their variants have been very successful for training deep learning models, such as neural networks. Meanwhile, given the nee…

cs.LG202123 cited

Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy

Xinwei Zhang, Xiangyi Chen, Mingyi Hong +2

Providing privacy protection has been one of the primary motivations of Federated Learning (FL). Recently, there has been a line of work on incorporating the formal privacy notion…

cs.LG2020

Understanding Gradient Clipping in Private SGD: A Geometric Perspective

Xiangyi Chen, Zhiwei Steven Wu, Mingyi Hong

Deep learning models are increasingly popular in many machine learning applications where the training data may contain sensitive information. To provide formal and rigorous privac…

cs.LG20208 cited

Private Stochastic Non-Convex Optimization: Adaptive Algorithms and Tighter Generalization Bounds

Yingxue Zhou, Xiangyi Chen, Mingyi Hong +2

We study differentially private (DP) algorithms for stochastic non-convex optimization. In this problem, the goal is to minimize the population loss over a -dimensional space gi…

cs.LG201934 cited

ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization

Xiangyi Chen, Sijia Liu, Kaidi Xu +4

The adaptive momentum method (AdaMM), which uses past gradients to update descent directions and learning rates simultaneously, has become one of the most popular first-order optim…