Xin Zhang

Xin Zhang

Research Scientist

AI and Applied Research, Meta Inc.

I’m currently a research scientist at AI and applied research in Meta, Inc. My work is about optimization and modeling for deep machine learning with application on recommendation system.

I got my Ph.D. degree from the Dept. of Statistics at Iowa State University advised by Dr. Zhengyuan Zhu and Dr. Jia Liu. Before that, I obtained my B.S in Mathematics from Fudan University, Shanghai, China.

Experience

 
 
 
 
 
Research Scientist
Meta, Inc.
January 2021 – Present Menlo Park, CA
 
 
 
 
 
Ph.D. Student in Statistics & Research Assistant
Iowa State University
August 2016 – May 2021 Ames, IA
 
 
 
 
 
Undergraduate Student in Mathematics
Fudan University
September 2012 – June 2016 Shanghai, China

Recent Publications

Weidong Liu, Xiaojun Mao, Xiaofei Zhang, Xin Zhang (2024). Robust Personalized Federated Learning with Sparse Penalization. Journal of the American Statistical Association (2024).

PDF Cite

Weidong Liu, Xiaojun Mao, Xiaofei Zhang, Xin Zhang (2024). Efficient Sparse Least Absolute Deviation Regression with Differential Privacy. IEEE Transactions on Information Forensics and Security (2024).

PDF Cite

Zhuqing Liu, Xin Zhang, Songtao Lu, Jia Liu (2023). PRECISION: Decentralized Constrained Min-Max Learning with Low Communication and Sample Complexities. In ACM Mobihoc 2023.

PDF Cite

Qinglong Tian, Xin Zhang, Jiwei Zhao (2023). ELSA: Efficient Label Shift Adaptation through the Lens of Semiparametric Models. In ICML 2022.

PDF Cite

Zhuqing Liu, Xin Zhang, Prashant Khanduri, Songtao Lu, Jia Liu (2023). Prometheus: Taming Sample and Communication Complexities in Constrained Decentralized Stochastic Bilevel Learning. In ICML 2023.

PDF Cite

See all publications

Featured Publications

Xin Zhang, Jia Liu, Zhengyuan Zhu
December, 2022 Journal of the American Statistical Association (2022):1-13
Learning Coefficient Heterogeneity over Networks: A Distributed Spanning-Tree-Based Fused-Lasso Regression
Learning Coefficient Heterogeneity over Networks: A Distributed Spanning-Tree-Based Fused-Lasso Regression

Identifying the latent cluster structure based on model heterogeneity is a fundamental but challenging task arises in many machine learning applications. In this article, we study the clustered coefficient regression problem in the distributed network systems, where the data are locally collected and held by nodes.
PDF Cite
Xin Zhang, Zhuqing Liu, Jia Liu, Zhengyuan Zhu, Songtao Lu
December, 2021 In Neurips 2021
Taming Communication and Sample Complexities in Decentralized Policy Evaluation for Cooperative Multi-Agent Reinforcement Learning
Taming Communication and Sample Complexities in Decentralized Policy Evaluation for Cooperative Multi-Agent Reinforcement Learning

Cooperative multi-agent reinforcement learning (MARL) has found many scientific and engineering applications. In this paper, we focus on decentralized MARL policy evaluation with nonlinear function approximation and propose efficient optimization algorithms.
PDF Cite

Projects

*
All Other
R Package: FlightScanner
Course project for STAT 585. Web scraping/crawling flight information from SkyScanner API (https://www.skyscanner.com/).
PDF Code
R Package: FlightScanner

Recent Posts

Hello R Markdown
R Markdown This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.
Dec 1, 2020 1 min read R
See all posts

Research Topics

Asynchronous Distributed Learning Bilevel Optimization Decentralized Learning Differential Privacy Federated Learning Gradient Delay Message Compression Sparse Learning Stochastic Optimization Variance Reduction

Gallery

Contact