Cis Home Page for Zhiwei Steven Wu

Steven Wu

Assistant Professor
School of Computer Science
Carnegie Mellon University


Email: zstevenwu [at] cmu.edu
Office: TCS Hall 424

I am an Assistant Professor in the School of Computer Science at Carnegie Mellon University, with my primary appointment in the Software and Societal Systems Department (with the Societal Computing program), and affiliated appointments with the Machine Learning Department and the Human-Computer Interaction Institute. I am also affiliated with the CyLab and the Theory Group.

I work on algorithms and machine learning. My recent work focuses on (1) how to make machine learning better aligned with societal values, especially privacy and fairness, and (2) how to make machine learning more reliable and robust when algorithms interact with social and economic dynamics. I study these questions using methods and models from learning theory, optimization, statistics, differential privacy, game theory, mechanism design, and human-computer interaction. For more details, please see my publications.

My research has been generously supported by the National Science Foundation (NSF), the Okawa Foundation, an Amazon Research Award, a Google Faculty Research Award, a J.P. Morgan Faculty Award, Facebook Research awards, a Mozilla Research Grant, Apple, and Cisco Research.

Previously, I received a Ph.D. in Computer Science in 2017 from the University of Pennsylvania, where I was extremely fortunate to have been co-advised by Michael Kearns and Aaron Roth. My doctoral dissertation titled "Data Privacy Beyond Differential Privacy" received Penn's Morris and Dorothy Rubinoff Award for best thesis. Before joining CMU, I was an Assistant Professor of Computer Science & Engineering at the University of Minnesota for two years. Before that, I spent a year as a post-doctoral researcher at Microsoft Research-New York City in the Machine Learning and Algorithmic Economics groups. Please see my CV for more details.


NEWS

Sept 2022

Seven papers accepted at NeurIPS 2022.

Aug 2022

Our paper Policy impacts of statistical uncertainty and privacy is now published in Science.

Aug 2022

I am giving several talks this summer: Google's FACT 2022 Conference, Google's FL seminar, the Privacy workshop at the Fields Institute in Toronto, the IMS Annual Meeting, and Baidu Research AI Colloquium.

June 2022

I gave a mini course on private synthetic data at the BU Summer School on Differential Privacy.

May 2022

Seven papers accepted at ICML 2022.


GROUP

I am extremely fortunate to be able to work with several excellent students.

PhD students

Giuseppe Vietri (co-advised by Maria Gini)
Daniel Ngo (co-advised by Maria Gini)
Logan Stapleton (co-advised by Haiyi Zhu)
Justin Whitehouse (co-advised by Aaditya Ramdas)
Keegan Harris (co-advised by Hoda Heidari)
Gokul Swamy (co-advised by Drew Bagnell)
Luke Guerdan (co-advised by Ken Holstein)
Terrance Liu

Postdocs

Pratiksha Thaker (co-advised by Virginia Smith)
Shuran Zheng (starting Jan 2023)

BS/MS Students

Xin Gu
Diana Qing

Alumni

Hao-Fei Cheng (PhD student), now at Amazon
Xinyan Hu (visiting undergrad), now a PhD student at UC Berkeley


TEACHING

Fall 2022

Fall 2021

Spring 2021

Fall 2020

Spring 2020

Fall 2019

Fall 2018


SERVICE

Conference Program Committee

NeurIPS 2022, 2021, 2020 (area chair)
ICML 2022, 2020 (area chair)
ICLR 2022, 2021, 2020 (area chair)
AISTATS 2021 (area chair)
ITCS 2022
SODA 2022
ALT 2021
FORC 2020
FAccT 2019, 2021 (area chair)
TheWebConf 2020, 2018
EC 2020, 2019, 2018

Workshop Program Committee

TPDP 2021, 2019
NIPSML4H18
HAI-GEN 2020

Workshop Organizer

Intersectionality in Fair Machine Learning: Where Are We and Where Should We Go from Here? MOSAIC 2020: An Annual Conference on Intersectionality. Nov. 1, 2020.

Recent Developments in Research on Fairness. The Simons Institute for the Theory of Computing, Berkeley, CA. July 8-10, 2019.

Other

I co-organize differentialprivacy.org.
During my undergraduate, I was involved in the Bard Prison Initiative as a math tutor at the Eastern New York Correctional Facility. Check out this amazing four-part documentary film series, College Behind Bars, about this initiative.


TALKS


Feb 2022

Of Moments and Matching: Trade-offs and Treatments in Imitation Learning
Simons Institute Workshop on Adversarial Approaches in Machine Learning
YouTube


Mar 2021

A Geometric View on Private Gradient-Based Optimization
Federated Learning One World Seminar (FLOW)
Google TechTalks
FLOW Video Google Video


Mar 2021

Feb 2021


Mar 2021
Feb 2021


Nov 2019

Between Individual and Group Fairness
Three Decades of DIMACS: The Journey Continues
Video


Oct 2019

Tutorial: Differential Privacy Techniques Beyond Differential Privacy
FOCS 2019 workshop A TCS Quiver
Slides


Jan 2018

Competing Bandits: Learning under Competition
ITCS 2018
Video


Aug 2017

Meritocratic Fairness for Cross-Population Selection
ICML 2017
Video


June 2017

Fairness Incentives for Myopic Agents
EC 2017
Video


June 2017

Multidimensional Dynamic Pricing for Welfare Maximization
EC 2017
Video