Research

Publications:

• “Having Confidence in My Confidence Intervals”: How Data Users Engage with Privacy-Protected Wikipedia Data. Harold Triedman, Jayshree Sarathy, Priyanka Nanayakkara, Rachel Cummings, Gabriel Kaptchuk, Sean Kross, Elissa M. Redmiles. Submitted 2025.
• Differentially Private Space-Efficient Algorithms for Counting Distinct Elements in the Turnstile Model. Rachel Cummings, Alessandro Epasto, Jieming Mao, Tamalika Mukherjee, Tingting Ou, Peilin Zhong. ICML 2025.
• Differential Privacy Under Class Imbalance: Methods and Empirical Insights. Lucas Rosenblatt, Yuliia Lut, Eitan Turok, Marco Avella-Medina, Rachel Cummings. ICML 2025.
• Models Matter: Setting Accurate Privacy Expectations for Local and Central Differential Privacy. Mary Anne Smart, Priyanka Nanayakkara, Rachel Cummings, Gabriel Kaptchuk, Elissa Redmiles. PETS 2025.
• Thompson Sampling is Itself Differentially Private. Tingting Ou, Marco Avella Medina, Rachel Cummings. AISTATS 2024.
• Integrating Contextual Integrity and Differential Privacy. Sebastian Benthall and Rachel Cummings. CS&Law 2024.
• Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment. Rachel Cummings, Damien Desfontaines, David Evans, Roxana Geambasu, Matthew Jagielski, Yangsibo Huang, Peter Kairouz, Gautam Kamath, Sewoong Oh, Olga Ohrimenko, Nicolas Papernot, Ryan Rogers, Milan Shen, Shuang Song, Weijie Su, Andreas Terzis, Abhradeep Thakurta, Sergei Vassilvitskii, Yu-Xiang Wang, Li Xiong, Sergey Yekhanin, Da Yu, Huanyu Zhang, Wanrong Zhang. Harvard Data Science Review 2024
• Centering Policy and Practice: Research Gaps around Usable Differential Privacy. Rachel Cummings and Jayshree Sarathy. IEEE TPS 2023.
• An Active Learning Framework for Multi-group Mean Estimation. Abdellah Aznag, Rachel Cummings, Adam Elmachtoub. NeurIPS 2023.
• What Are the Chances? Explaining the Epsilon Parameter in Differential Privacy. Priyanka Nanayakkara, Mary Anne Smart, Rachel Cummings, Gabriel Kaptchuk, Elissa Redmiles. USENIX Security 2023.
• Robust Estimation under the Wasserstein Distance. Sloan Nietert, Rachel Cummings, and Ziv Goldfeld. Submitted, 2023.
• The Privacy Elasticity of Behavior: Conceptualization and Application. Inbal Dekel, Rachel Cummings, Ori Heffetz, and Katrina Ligett. EC 2023.
• Differentially Private Synthetic Control. Saeyoung Rho, Rachel Cummings, and Vishal Misra. AISTATS, 2023. Journal version: Journal of Privacy and Confidentiality, 2024.
• Optimal Data Acquisition with Privacy-Aware Agents. Rachel Cummings, Hadi Elzayn, Vasilis Gkatzelis, Emmanouil Pountourakis, Juba Ziani. SaTML, 2023. Best Paper Award
• Multi-Layer Influence Network Modeling of Critical Infrastructure Interdependencies. Zixing Wang, Rachel Cummings, and Chelsea C. White III. Submitted, 2022.
• Mean Estimation with User-Level Privacy under Data Heterogeneity. Rachel Cummings, Vitaly Feldman, Audra McMillan, and Kunal Talwar. NeurIPS, 2022.
• Private Sequential Hypothesis Testing for Statisticians: Privacy, Error, and Sample Size. Wanrong Zhang, Yajun Mei, and Rachel Cummings. AISTATS, 2022.
• Outlier-Robust Optimal Transport: Duality, Structure, and Statistical Analysis. Sloan Nietert, Rachel Cummings, and Ziv Goldfeld. AISTATS, 2022.
• How we browse: Measurement and analysis of digital behavior. Yuliia Lut, Michael Wang, Elissa Redmiles, and Rachel Cummings. IEEE CogMI, 2024.
• Attribute Privacy: Framework and Mechanisms. Wanrong Zhang, Olga Ohrimenko, and Rachel Cummings. FAccT 2022.
• Optimal Local Explainer Aggregation for Interpretable Prediction. Qiaomei Li, Rachel Cummings, and Yonatan Mintz. AAAI 2022.  (Preliminary version was titled “Locally Interpretable Predictions of Parkinson’s Disease Progression”.)
• “I need a better description”: An Investigation Into User Expectations For Differential Privacy. Rachel Cummings, Gabriel Kaptchuk, and Elissa Redmiles. CCS 2021. Best Paper Award, Runner Up. Journal version: Journal of Privacy and Confidentiality, 2023.
• Differentially Private Normalizing Flows for Privacy-Preserving Density Estimation. Chris Waits and Rachel Cummings. AIES 2021.
• Differentially Private Online Submodular Maximization. Sebastian Perez-Salazar and Rachel Cummings. AISTATS 2021.
• PAPRIKA: Private Online False Discovery Rate Control. Wanrong Zhang, Gautam Kamath, and Rachel Cummings. ICML 2021.
• Differentially Private Synthetic Mixed-Type Data Generation for Unsupervised Learning. Uthaipon (Tao) Tantipongpipat, Chris Waites, Digvijay Boob, Amaresh (Ankit) Siva, and Rachel Cummings. IISA 2021. Journal version: Intelligent Decision Technologies, 2022.
• Privately Detecting Changes in Unknown Distributions. Rachel Cummings, Sara Krehbiel, Yuliia Lut, and Wanrong Zhang. ICML 2020.
• Single and Multiple Change-Point Detection with Differential Privacy. Wanrong Zhang, Sara Krehbiel, Rui Tuo, Yajun Mei, and Rachel Cummings. JMLR, 2021. (Preliminary version appeared at NeurIPS 2018)
• Algorithmic Price Discrimination. Rachel Cummings, Nikhil Devanur, Zhiyi Huang, and Xiangning Wang. SODA 2020.
• Individual Sensitivity Preprocessing for Data Privacy. Rachel Cummings and David Durfee. SODA 2020.
• Advances and Open Problems in Federated Learning. Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Keith Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, Rafael G.L. D’Oliveira, Salim El Rouayheb, David Evans, Josh Gardner, Zachary Garrett, Adrià Gascón, Badih Ghazi, Phillip B. Gibbons, Marco Gruteser, Zaid Harchaoui, Chaoyang He, Lie He, Zhouyuan Huo, Ben Hutchinson, Justin Hsu, Martin Jaggi, Tara Javidi, Gauri Joshi, Mikhail Khodak, Jakub Konečný, Aleksandra Korolova, Farinaz Koushanfar, Sanmi Koyejo, Tancrède Lepoint, Yang Liu, Prateek Mittal, Mehryar Mohri, Richard Nock, Ayfer Özgür, Rasmus Pagh, Mariana Raykova, Hang Qi, Daniel Ramage, Ramesh Raskar, Dawn Song, Weikang Song, Sebastian U. Stich, Ziteng Sun, Ananda Theertha Suresh, Florian Tramèr, Praneeth Vepakomma, Jianyu Wang, Li Xiong, Zheng Xu, Qiang Yang, Felix X. Yu, Han Yu, Sen Zhao. Foundations and Trends in Machine Learning, 2021
• Learning Auctions with Robust Incentive Guarantees. Jacob Abernethy, Rachel Cummings, Bhuvesh Kumar, Jamie Morgenstern, and Sam Taggart. NeurIPS 2019.
• On the Compatibility of Privacy and Fairness. Rachel Cummings, Varun Gupta, Dhamma Kimpara, and Jamie Morgenstern. FairUMAP 2019.
• Differentially Private Online Submodular Minimization. Adrian Rivera Cardoso and Rachel Cummings.  AISTATS ’19.
• Private Synthetic Data Generation via GANs. Digvijay Boob, Rachel Cummings, Dhamma Kimpara, Uthaipon (Tao) Tantipongpipat, Chris Waites, and Kyle Zimmerman. NIST Unlinkable Data Challenge, 2018. Winner: Grand Prize; Winner: People’s Choice Award.
• The Role of Differential Privacy in GDPR Compliance. Rachel Cummings and Deven Desai. FATREC ’18.
• Differentially Private Change-Point Detection. Rachel Cummings, Sara Krehbiel, Yajun Mei, Rui Tuo, and Wanrong Zhang. NeurIPS ’18.
• Differential Privacy for Growing Databases. Rachel Cummings, Sara Krehbiel, Kevin Lai, and Uthaipon (Tao) Tantipongpipat.  NeurIPS ’18.
• Differential Privacy as a Tool for Truthfulness in Games.  Rachel Cummings. XRDS 2017.
• Adaptive Learning with Robust Generalization Guarantees. Rachel Cummings, Katrina Ligett, Kobbi Nissim, Aaron Roth, and Zhiwei Steven Wu. COLT ’16.
• The Possibilities and Limitations of Private Prediction Markets. Rachel Cummings, David Pennock and Jennifer Wortman Vaughan. EC ’16.  Journal version: TEAC (by invitation), 2021.
• The Strange Case of Privacy in Equilibrium Models. Rachel Cummings, Katrina Ligett, Mallesh Pai, and Aaron Roth. EC ’16.
• Coordination Complexity: Small Information Coordinating Large Populations. Rachel Cummings, Katrina Ligett, Jaikumar Radhakrishnan, Aaron Roth, and Zhiwei Steven Wu. ITCS ’16.
• Truthful Linear Regression. Rachel Cummings, Stratis Ioannidis and Katrina Ligett. COLT ’15.
• Accuracy for Sale: Aggregating Data with a Variance Constraint. Rachel Cummings, Katrina Ligett, Aaron Roth, Zhiwei Steven Wu, and Juba Ziani. ITCS ’15.
• Privacy and Truthful Equilibrium Selection for Aggregative Games. Rachel Cummings, Michael Kearns, Aaron Roth, and Zhiwei Steven Wu. WINE ’15.
• Online Learning and Profit Maximization from Revealed Preferences. Kareem Amin, Rachel Cummings, Lili Dworkin, Michael Kearns, and Aaron Roth. AAAI ’15.
• Probability 1 Computation with Chemical Reaction Networks. Rachel Cummings, Dave Doty and David Soloveichik. DNA ’14.  Journal version: Natural Computing 2015.
• The Empirical Implications of Privacy-Aware Choice. Rachel Cummings, Federico Echenique and Adam Wierman. EC ’14.  Journal version: Operations Research, 2016.
• Speed Faults in Computation by Chemical Reaction Networks. Ho-Lin Chen, Rachel Cummings, Dave Doty, and David Soloveichik. DISC ’14. Best paper award.  Journal version: Distributed Computing, 2015.
• Influence Maximization in Social Networks When Negative Opinions May Emerge and Propagate.  Wei Chen, Alex Collins, Rachel Cummings, Te Ke, Zhenming Liu, David Rincon, Xiaorui Sun, Yajun Wang, Wei Wei, and Yifei Yuan. SDM’11.

Policy Reports and Public Comments:

• A Community-Driven Differential Privacy Deployment Registry. Micah Altman, Sharon Ayalde, Rachel Cummings, Damien Desfontaines, Jack Fitzsimons, Elena Ghazi, Andrew Gruen, James Honaker, Gary Howarth, Nitin Kohli, Chuck McCallum, Priyanka Nanayakkara, Joseph P. Near, Robert Pisarczyk, Salil Vadhan. NIST Internal Report 8588. Sept 2025.
• Increasing Responsible Data Sharing throughout Government. Rachel Cummings, Shlomi Hod, Palak Jain, Gabriel Kaptchuk, Tamalika Mukherjee, Priyanka Nanayakkara, Jayshree Sarathy, and Jeremy Seeman. Federation of American Scientists, Day One Memo. Mar 2025.
• Response to the RFI on Executive Branch Agency Handling of Commercially Available Information Containing Personally Identifiable Information. Rachel Cummings, Shlomi Hod, Palak Jain, Gabriel Kaptchuk, Tamalika Mukherjee, Priyanka Nanayakkara, and Jayshree Sarathy. Dec 2024.
• Comment on “NIST SP 800-226: Guidelines for Evaluating Differential Privacy Guarantees”. Rachel Cummings, Shlomi Hod, Gabriel Kaptchuk, Priyanka Nanayakkara, Jayshree Sarathy, and Jeremy Seeman. Mar 2024.
• Modern solutions to modern problems: leveraging the latest in data privacy and algorithmic fairness. Comment on “FTC Trade Regulation Rule on Commercial Surveillance and Data Security. Rachel Cummings. Nov 2022.

Theses:

• The Implications of Privacy-Aware Choice.  Rachel Cummings. Ph.D. Thesis, Caltech 2017.  Winner: Amori Doctoral Prize in Computing and Mathematical Sciences; Honorable Mention: SIGecom Doctoral Dissertation Award