Wei-Ning Chen (陳偉寧)

I am a final year Electrical Engineering PhD student at Stanford University advised by Ayfer Özgür and supported by a 3-year Stanford Graduate Fellowhip (SGF). My research focuses on information theory, statistics and theoretical machine learning, with applications to differential privacy and federated learning/ anlytics. Before joining Stanford, I obtained a master degree in Electrical Engineering from National Taiwan University. Prior to that, I received bachelor's degrees in Electric Engineering and Mathematics from the same university in 2016.

In 2023 summer and Fall, I was a student researcher at Google working on copyright protection for language models. In 2022 summer, I worked as a research intern at Meta, hosted by Graham Cormode and Akash Bharadwaj. Prior to that, I spent 2021 summer and fall at Google as a research intern, hosted by Peter Kairouz.

Outside lab, I play volleyball and badminton and enjoy all kinds of outdoor activities. Recently, I start photographing.

I will be on the job market starting in Fall 2024 and am looking for research positions in industry or academia. Feel free to reach out!

Research Interest

I am broadly interested in information-theoretic and algorithmic aspects of data science, and my current focus lies on differential privacy and federated learning/analytics. My research adopts tools from information theory, theoretical machine learning and high-dimensional statistics.

Contact

Email: wnchen [at] stanford [dot] edu

Packard Building, Room No. 201
350 Serra Mall
Stanford, CA 94305

News

[Mar. 2024] I will give a (invited) talk at IZS 2024 in Zurich!
[Jan. 2024] A paper accepted to AISTATS 2024!
[Dec. 2023] I will present three posters in NeurIPS at New Orleans.
[Oct. 2023] I will present a (invited) poster in Asilomar Conference at Monterey.
[Sept. 2023] I will present four posters TPDP 2023 at Boston.
[Sept. 2023] Three papers accepted to NeurIPS 2023!

Invited Talks

“Achieving Joint Privacy and Communication Efficiency in Federated Learning and Analytics,” Conference on Information Sciences and Systems (CISS), March 2023.
“On the Optimal Communication Cost in Private Federated Learning and Analytics,” Information Theory and Data Science Workshop (National University of Singapore), January 2023.
“On the Optimal Communication Cost in Private Federated Learning and Analytics,” National Taiwan University, December 2022.
“On the Optimal Communication Cost in Private Federated Learning,” at ITW invited talk (student research), October 2022.
“The Communication Cost of Security and Privacy in Federated Frequency Estimation,” at Google Research, September 2022.
“The Poisson Binomial Mechanism for Unbiased Federated Learning with Secure Aggregation,” at Meta RAI, July 2022.
“Fundamental Limits of Distributed Estimation under Information Constraints: beyond the Worst-case Analysis,” at Google Research, September 2021.
“Distributed Estimation under Information Constraints,” at National Taiwan University, December 2020.

Professional Activities

Reviewer for ICLR 2021, ITCS 2021, ICML 2021-2023, AISTATS 2022-2023, ALT 2021, NeurIPS 2021-2022, ISIT 2021-2023, WCNC 2022, ICC 2018
Area chair for ICML 2021 ITR3 workshop
Reviewer for IEEE Transactions on Knowledge and Data Engineering, IEEE Transactions on Information Theory