activity
20192022
most citedTowards Plausible Differentially Private ADMM Based Distributed Machine Learning

9 citations · 15 across the 6 of their papers we have counts for

collaborators

9 papers

cs.IR2022

Meta-Shop: Improving Item Advertisement For Small Businesses

Yang Shi, Guannan Liang, Young-joo Chung

In this paper, we study item advertisements for small businesses. This application recommends prospective customers to specific items requested by businesses. From analysis, we fou…

math.OC20211 cited

Escaping Saddle Points with Stochastically Controlled Stochastic Gradient Methods

Guannan Liang, Qianqian Tong, Chunjiang Zhu +1

Stochastically controlled stochastic gradient (SCSG) methods have been proved to converge efficiently to first-order stationary points which, however, can be saddle points in nonco…

cs.LG2021

An Efficient Algorithm for Deep Stochastic Contextual Bandits

Tan Zhu, Guannan Liang, Chunjiang Zhu +2

In stochastic contextual bandit (SCB) problems, an agent selects an action based on certain observed context to maximize the cumulative reward over iterations. Recently there have…

cs.LG20205 cited

Federated Nonconvex Sparse Learning

Qianqian Tong, Guannan Liang, Tan Zhu +1

Nonconvex sparse learning plays an essential role in many areas, such as signal processing and deep network compression. Iterative hard thresholding (IHT) methods are the state-of-…

math.OC2020

Asynchronous Parallel Stochastic Quasi-Newton Methods

Qianqian Tong, Guannan Liang, Xingyu Cai +2

Although first-order stochastic algorithms, such as stochastic gradient descent, have been the main force to scale up machine learning models, such as deep neural nets, the second-…

cs.LG2020

Effective Proximal Methods for Non-convex Non-smooth Regularized Learning

Guannan Liang, Qianqian Tong, Jiahao Ding +2

Sparse learning is a very important tool for mining useful information and patterns from high dimensional data. Non-convex non-smooth regularized learning problems play essential r…