activity
20182024
most citedVariance Reduced Median-of-Means Estimator for Byzantine-Robust Distributed Inference

12 citations · 34 across the 9 of their papers we have counts for

collaborators
Showing stat.MLShow all

6 papers · 1 filter

stat.ML20244 cited

Efficient Sparse Least Absolute Deviation Regression with Differential Privacy

Weidong Liu, Xiaojun Mao, Xiaofei Zhang +1

In recent years, privacy-preserving machine learning algorithms have attracted increasing attention because of their important applications in many scientific fields. However, in t…

stat.ML202211 cited

Fast and Robust Sparsity Learning over Networks: A Decentralized Surrogate Median Regression Approach

Weidong Liu, Xiaojun Mao, Xin Zhang

Decentralized sparsity learning has attracted a significant amount of attention recently due to its rapidly growing applications. To obtain the robust and sparse estimators, a natu…

stat.ML20211 cited

Matrix Completion with Model-free Weighting

Jiayi Wang, Raymond K. W. Wong, Xiaojun Mao +1

In this paper, we propose a novel method for matrix completion under general non-uniform missing structures. By controlling an upper bound of a novel balancing error, we construct…

stat.ML202112 cited

Variance Reduced Median-of-Means Estimator for Byzantine-Robust Distributed Inference

Jiyuan Tu, Weidong Liu, Xiaojun Mao +1

This paper develops an efficient distributed inference algorithm, which is robust against a moderate fraction of Byzantine nodes, namely arbitrary and possibly adversarial machines…

stat.ML20202 cited

Median Matrix Completion: from Embarrassment to Optimality

Weidong Liu, Xiaojun Mao, Raymond K. W. Wong

In this paper, we consider matrix completion with absolute deviation loss and obtain an estimator of the median matrix. Despite several appealing properties of median, the non-smoo…

stat.ML2018

Matrix Completion under Low-Rank Missing Mechanism

Xiaojun Mao, Raymond K. W. Wong, Song Xi Chen

Matrix completion is a modern missing data problem where both the missing structure and the underlying parameter are high dimensional. Although missing structure is a key component…