Jamie Morgenstern

Assistant Professor in the Paul G. Allen School of Computer Science & Engineering
at the University of Washington
Office:

Email: 'jamiemmt' 'at' 'cs 'dot' 'washington' 'dot' 'edu'


I am an assistant professor in the Paul G. Allen School of Computer Science & Engineering at the University of Washington. I was previously an assistant professor in the School of Computer Science at Georgia Tech. Prior to starting as faculty, I was fortunate to be hosted by Michael Kearns, Aaron Roth, and Rakesh Vohra as a Warren Center fellow at the University of Pennsylvania. I completed my PhD working with Avrim Blum at Carnegie Mellon University. I study the social impact of machine learning and the impact of social behavior on ML's guarantees. How should machine learning be made robust to behavior of the people generating training or test data for it? How should ensure that the models we design do not exacerbate inequalities already present in society?

Working papers

Multi-learner risk reduction under endogenous participation dynamics. Sarah Dean, Mihaela Curmei, Lillian J. Ratliff, Jamie Morgenstern, Maryam Fazel
Optimal Spend Rate Estimation and Pacing for Ad Campaigns with Budgets. Bhuvesh Kumar, Jamie Morgenstern and Okke Schrijvers.
Predictive Inequity in Object Detection , joint with Benjamin Wilson and Judy Hoffman. Code can be found here. News coverage in Vox, Businesss Insider, The Guardian, NBC News.

White papers

Facial Recognition Technologies in the Wild: A Call for a Federal Office, Erik Learned-Miller, Vicente Ordóñez, Jamie Morgenstern, and Joy Buolamwini.
Committee for the Study of Digital Platforms, Market Structure and Antitrust Subcommittee Report, joint with Fiona Scott Morton (chair), Theodore Nierenberg, Pascal Bouvier, Ariel Ezrachi, Bruno Jullien, Roberta Katz, Gene Kimmelman, and A. Douglas Melamed.

Mentoring

I'm very fortunate to have worked with the following excellent students.

Current students:

Rachel Hong (PhD)
Jie (Claire) Zhang (PhD)
Yuanyuan (Chloe) Yang (PhD)

Past students and visitors:

Daniel Jiang (MS)
Bhuvesh Kumar (PhD, SCS, joint with Jake Abernethy)
Aditya Saraf (MS)
Benjamin Wilson (MS)
Angel (Alex) Cabrera (BS)
Varun Gupta (BS)
Dhamma Kimpara (BS)

Postdoctoral researchers


Min Jae Song
Matthäus Kleindessner
Sarah Dean

Service

In 2020, I was an area chair for ICML, on the SPC for EC, ICLR, and COLT. I served as general cochair for FAT* 2019, which took place in Atlanta! In 2019, I served as an SPC member for EC and ICML. For 2018, I was on the PC for EC, ICML, FAT*, WWW, and ALT. In 2017, I was on the PC for EC, ICML, NetEcon, and FAT/ML. I also served on the EC PC in 2016.

Funding

My research is currently supported by: An NSF Career award, "Strategic and Equity Considerations in Machine Learning". The Institute for Foundations of Machine Learning, an NSF-funded AI Center joint between UT Austin, UW, Witchitaw State, and Microsoft Research. The Theory of Computing for Fairness, A Simons collaboration project. Previously, I was fortunate to be supported by the Simons Award for Graduate Students in Theoretical Computer Science (2014-2016), an NSF GFRP fellowship, as well as the Microsoft Research Graduate Women's Scholarship.

Publications

NeurIPS 2023 Doubly Constrained Fair Clustering John Dickerson, Seyed Esmaeili, Jamie Morgenstern, Claire Jie Zhang
NeurIPS 2023 Scalable Membership Inference Attacks via Quantile Regression. Martin Bertran, Shuai Tang, Aaron Roth, Michael Kearns, Jamie Morgenstern, Steven Wu
AIES 2023 Evaluation of targeted dataset collection on racial equity in face recognition. Rachel Hong, Tadayohsi Kohno, and Jamie Morgenstern.
AIES 2023 Multicalibrated Regression for Downstream Fairness. Ira Globus-Harris and Varun Gupta and Christopher Jung and Michael Kearns and Jamie Morgenstern and Aaron Roth.
FORC 2023 Distributionally Robust Data Join. Pranjal Awasthi, Christopher Jung, Jamie Morgenstern.
NeurIPS 2022 Active learning with Safety ConstraintsRomain Camilleri, Andrew Wagenmaker, Jamie Morgenstern, Lalit Jain, Kevin Jamieson.
ICML 2022 Individual Preference Stability for ClusteringSaba Ahmadi, Pranjal Awasthi, Samir Khuller, Matthäus Kleindessner, Jamie Morgenstern, Pattara Sukprasert, Ali Vakilian
ICML 2022 Active Sampling for Min-Max Fairness. Jacob Abernethy, Pranjal Awasthi, Matthäus Kleindessner,Jamie Morgenstern, Chris Russel, Claire Zhang.
EC 2022 Preference Dynamics Under Personalized Recommendations. Sarah Dean and Jamie Morgenstern.
FaccT 2021 Evaluating Fairness of Machine Learning Models Under Uncertain and Incomplete Information. Pranjal Awasthi, Alex Beutel, Matthäus Kleindessner, Jamie Morgenstern, and Xuezhi Wang.
CACM 2021 Datasheets for Datasets. Timnit Gebru, Jamie Morgenstern, Briana Vecchione, Jennifer Wortman Vaughan, Hanna Wallach, Hal Daumé III, Kate Crawford.
AISTATS 2020 Equalized odds postprocessing under imperfect group information. Pranjal Awasthi, Matthäus Kleindessner, Jamie Morgenstern.
WINE 2020 Competition Alleviates Present Bias in Task Completion. Aditya Saraf, Anna Karlin, and Jamie Morgenstern.
AIES (AI, Ethics and Society) 2020 Diversity and Inclusion in Subset Selection. Alex Hanna, Dylan Baker, Emily Denton, Nyalleng Moorosi, Ben Hutchinson, Timnit Gebru, Meg Mitchell, Jamie Morgenstern.
NeurIPS 2019 Learning Auctions with Incentive Guarantees. Jacob Abernethy, Rachel Cummings, Bhuvesh Kumar, Jamie Morgenstern, Samuel Taggart.
NeurIPS 2019 Multi-Criteria Dimensionality Reduction with Applications to Fairness Jamie Morgenstern, Samira Samadi, Mohit Singh, Uthaipon Tantipongpipat, Santosh Vempala.
VIS 2019 FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learning. Ángel Alexander Cabrera, Will Epperson, Fred Hohman, Minsuk Kahng, Jamie Morgenstern, Duen Horng Chau.
ICML 2019 Guarantees for Spectral Clustering with Fairness Constraints. Matthäus Kleindessner, Samira Samadi, Pranjal Awasthi, Jamie Morgenstern.
ICML 2019 Fair k-center clustering for data summarization. Matthäus Kleindessner, Pranjal Awasthi, Jamie Morgenstern.
NeurIPS 2018 The Price of Fair PCA: One Extra Dimension. Samira Samadi, Uthaipon Tantipongpipat, Mohit Singh, Jamie Morgenstern, and Santosh Vempala.
NeurIPS 2018 A Smoothed Analysis of the Greedy Algorithm. Sampath Kannan, Jamie Morgenstern, Aaron Roth, Boes Waggoner, and Steven Wu.
ICML 2017 Fairness in Reinforcement Learning. Shahin Jabbari, Matthew Joseph, Michael Kearns, Jamie Morgenstern, and Aaron Roth.
EC 2017Fairness Incentives for Myopic Agents. Sampath Kannan, Michael Kearns, Jamie Morgenstern, Mallesh Pai, Aaron Roth, Rakesh Vohra, and Zhiwei Steven Wu.arxiv
WINE 2016 Strategic Network Formation with Attack and Immunization Sanjeev Goyal, Shahin Jabbari, Michael Kearns, Sanjeev Khanna, Jamie Morgenstern.arxiv
NeurIPS 2016 Fairness in Learning: Classic and Contextual Bandits. Matthew Joseph, Michael Kearns, Jamie Morgenstern, and Aaron Roth.arxiv
EC 2016Simple Mechanisms for Agents with Complements Michal Feldman, Ophir Friedler, Jamie Morgenstern, Guy Reinerarxiv
COLT 2016Learning Simple Auctions Jamie Morgenstern, Tim Roughgardenarxiv
STOC 2016Do Prices Coordinate Markets? (short version)Justin Hsu, Jamie Morgenstern, Ryan Rogers, Aaron Roth, Rakesh Vohraarxiv
NeurIPS 2015 The Pseudo-Dimension of Nearly Optimal Auctions

Selected for a spotlight presentation, along with 3.6% of submissions.

Jamie Morgenstern and Tim Roughgardenarxiv
EC 2015Private Pareto-Optimal ExchangeSampath Kannan, Jamie Morgenstern, Ryan Rogers, and Aaron Rotharxiv
EC 2015Simple Auctions with Simple StrategiesNikhil Devanur, Jamie Morgenstern, Vasilis Syrgkanis, S. Matthew Weinberg
EC 2015Learning What's Going On: Reconstruction Preferences and Priorities from Opaque TransactionsAvrim Blum, Yishay Mansour, Jamie Morgensternarxiv
IJCAI 2015Impartial Peer ReviewDavid Kurokawa, Omer Lev, Jamie Morgenstern, Ariel Procaccia
SODA 2015Approximately Stable, School Optimal, and Student-Truthful Many-to-One Matchings (via Differential Privacy)Sampath Kannan, Jamie Morgenstern, Aaron Roth, Steven Wuarxiv
AAAI 2015Learning Valuation Distributions from Partial ObservationAvrim Blum, Yishay Mansour, Jamie Morgensternarxiv
ITCS 2015Privacy-preserving Public Information in Sequential GamesAvrim Blum, Jamie Morgenstern, Ankit Sharma, Adam Smitharxiv
AAAI 2013How Bad is Selfish Voting?Simina Brânzei, Ioannis Caragiannis, Jamie Morgenstern, Ariel D. Procaccia
COSN 2013 Hierarchical community decomposition via oblivious routing techniques William Sean Kennedy, Jamie Morgenstern, Gordon Wilfong, Lisa Zhang
APPROX 2012Additive Approximation for Near-Perfect Phylogeny ConstructionPranjal Awasthi, Avrim Blum, Jamie Morgenstern, Or Sheffet
AAAI 2012On Maxsum Fair Cake DivisionsSteven J. Brams, Michal Feldman, John K. Lai, Jamie Morgenstern, Ariel D. Procaccia
STM 2011A proof-carrying File system with Revocable and Use-once Certificates (Conference on Security and Trust Management)Jamie Morgenstern, Deepak Garg, Frank Pfenning
ICFP 2010Security-typed Programming Within Dependently Typed ProgrammingJamie Morgenstern, Dan Licata

Workshops

DebugML 2019, colocated with ICLR. Discovery of Intersectional Bias in Machine Learning Using Automatic Subgroup Generation. Angel Cabrera, Minsuk Kahng, Fred Hohman, Jamie Morgenstern and Duen Horng Chau.

FairUMAP 2019. On the Compatibility of Privacy and Fairness. Rachel Cummings, Varun Gupta, Dhamma Kimpara, Jamie Morgenstern.

Thesis

Ph.D, Market Algorithms: Incentives, Learning, and Privacy (Defended May 2015)
Original CMU Tech Report (Not updated for typos)