Publications by Group Members

Tosca Lechner, Alex Bie, Gautam Kamath (2025). On the Learnability of Distribution Classes with Adaptive Adversaries. Proceedings of the 42nd International Conference on Machine Learning (ICML 2025).

Valentio Iverson, Gautam Kamath, Argyris Mouzakis (2025). Optimal Differentially Private Sampling of Unbounded Gaussians. Proceedings of the 38th Annual Conference on Learning Theory (COLT 2025).

Jie Zhang, Debeshee Das, Gautam Kamath, Florian Tramèr (2025). Position: Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data. Proceedings of the 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML 2025).

Xin Gu, Gautam Kamath, Zhiwei Steven Wu (2025). Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance. Proceedings of the 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML 2025).

Christian Janos Lebeda, Matthew Regehr, Gautam Kamath, Thomas Steinke (2025). Avoiding Pitfalls for Privacy Accounting of Subsampled Mechanisms under Composition. Proceedings of the 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML 2025).

Christian Covington, Xi He, James Honaker, Gautam Kamath (2025). Unbiased Statistical Estimation and Valid Confidence Intervals Under Differential Privacy. Statistica Sinica.

Sushant Agarwal, Gautam Kamath, Mahbod Majid, Argyris Mouzakis, Rose Silver, Jonathan Ullman (2025). Private Mean Estimation with Person-Level Differential Privacy. Proceedings of the 36th Annual ACM-SIAM Symposium on Discrete Algorithms (SODA 2025).

Gautam Kamath (2024). The Broader Landscape of Robustness in Algorithmic Statistics. arXiv preprint arXiv:2412.02670.

Yihan Wang, Yiwei Lu, Xiao-Shan Gao, Gautam Kamath, Yaoliang Yu (2024). BridgePure: Revealing the Fragility of Black-box Data Protection. arXiv preprint arXiv:2412.21061.

Sara Kodeiri (2024). Towards Standardized Evaluation in Differentially Private Image Classification: A Critical Approach.

Sabrina Mokhtari (2024). Revisiting Benchmarks for Privacy-Preserving Image Classification.

Florian Tramèr, Gautam Kamath, Nicholas Carlini (2024). Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining. Proceedings of the 41st International Conference on Machine Learning (ICML 2024).

Yiwei Lu, Matthew Y.R. Yang, Zuoqiu Liu, Gautam Kamath, Yaoliang Yu (2024). Disguised Copyright Infringement of Latent Diffusion Models. Proceedings of the 41st International Conference on Machine Learning (ICML 2024).

Ruicheng Xian, Qiaobo Li, Gautam Kamath, Han Zhao (2024). Differentially Private Post-Processing for Fair Regression. Proceedings of the 41st International Conference on Machine Learning (ICML 2024).

Martin Pawelczyk, Jimmy Z Di, Yiwei Lu, Gautam Kamath, Ayush Sekhari, Seth Neel (2024). Machine Unlearning Fails to Remove Data Poisoning Attacks. arXiv preprint arXiv:2406.17216.

Da Yu, Saurabh Naik, Arturs Backurs, Sivakanth Gopi, Huseyin A Inan, Gautam Kamath, Janardhan Kulkarni, Yin Tat Lee, Andre Manoel, Lukas Wutschitz, Sergey Yekhanin, Huishuai Zhang (2024). Differentially Private Fine-tuning of Language Models. Journal of Privacy and Confidentiality.

Yiwei Lu, Matthew Y.R. Yang, Gautam Kamath, Yaoliang Yu (2024). Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors. Proceedings of the 2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML 2024).

Mark Bun, Gautam Kamath, Argyris Mouzakis, Vikrant Singhal (2024). Not All Learnable Distribution Classes are Privately Learnable. Proceedings of the 35th International Conference on Algorithmic Learning Theory (ALT 2024).

Vikrant Singhal (2024). A Polynomial Time, Pure Differentially Private Estimator for Binary Product Distributions. Proceedings of the 35th International Conference on Algorithmic Learning Theory (ALT 2024).

Chris Trevisan (2024). Sorting and Selection in Rounds with Adversarial Comparisons. Proceedings of the 35th Annual ACM-SIAM Symposium on Discrete Algorithms (SODA 2024).

Alex Bie (2024). Private Distribution Learning with Public Data.

Rachel Cummings, Damien Desfontaines, David Evans, Roxana Geambasu, Yangsibo Huang, Matthew Jagielski, 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 (2024). Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment. Harvard Data Science Review.

Shai Ben-David, Alex Bie, Clément L. Canonne, Gautam Kamath, Vikrant Singhal (2023). Private Distribution Learning with Public Data: The View from Sample Compression. Advances in Neural Information Processing Systems 36 (NeurIPS 2023).

Jimmy Z. Di, Jack Douglas, Jayadev Acharya, Gautam Kamath, Ayush Sekhari (2023). Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks. Advances in Neural Information Processing Systems 36 (NeurIPS 2023).

Shai Ben-David, Alex Bie, Gautam Kamath, Tosca Lechner (2023). Distribution Learnability and Robustness. Advances in Neural Information Processing Systems 36 (NeurIPS 2023).

A Feder Cooper, Katherine Lee, James Grimmelmann, Daphne Ippolito, Christopher Callison-Burch, Christopher A Choquette-Choo, Niloofar Mireshghallah, Miles Brundage, David Mimno, Madiha Zahrah Choksi, Jack M Balkin, Nicholas Carlini, Christopher De Sa, Jonathan Frankle, Deep Ganguli, Bryant Gipson, Andres Guadamuz, Swee Leng Harris, Abigail Z Jacobs, Elizabeth Joh, Gautam Kamath, Mark Lemley, Cass Matthews, Christine McLeavey, Corynne McSherry, Milad Nasr, Paul Ohm, Adam Roberts, Tom Rubin, Pamela Samuelson, Ludwig Schubert, Kristen Vaccaro, Luis Villa, Felix Wu, Elana Zeide (2023). Report of the 1st Workshop on Generative AI and Law. arXiv preprint arXiv:2311.06477.

Alex Bie, Gautam Kamath, Guojun Zhang (2023). Private GANs, Revisited. Transactions on Machine Learning Research.

Da Yu, Gautam Kamath, Janardhan Kulkarni, Tie-Yan Liu, Jian Yin, Huishuai Zhang (2023). Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent. Transactions on Machine Learning Research.

Matthew Regehr (2023). A Bias-Variance-Privacy Trilemma for Statistical Estimation.

Yiwei Lu, Gautam Kamath, Yaoliang Yu (2023). Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks. Proceedings of the 40th International Conference on Machine Learning (ICML 2023).

Samuel B Hopkins, Gautam Kamath, Mahbod Majid, Shyam Narayanan (2023). Robustness Implies Privacy in Statistical Estimation. Proceedings of the 55th Annual ACM Symposium on the Theory of Computing (STOC 2023).

Mahbod Majid (2023). Efficient and Differentially Private Statistical Estimation via a Sum-of-Squares Exponential Mechanism.

Gautam Kamath, Argyris Mouzakis, Matthew Regehr, Vikrant Singhal, Thomas Steinke, Jonathan Ullman (2023). A Bias-Variance-Privacy Trilemma for Statistical Estimation. arXiv preprint arXiv:2301.13334.

Alex Bie, Gautam Kamath, Vikrant Singhal (2022). Private Estimation with Public Data. Advances in Neural Information Processing Systems 35 (NeurIPS 2022).

Gautam Kamath, Argyris Mouzakis, Vikrant Singhal (2022). New Lower Bounds for Private Estimation and a Generalized Fingerprinting Lemma. Advances in Neural Information Processing Systems 35 (NeurIPS 2022).

Yiwei Lu, Gautam Kamath, Yaoliang Yu (2022). Indiscriminate Data Poisoning Attacks on Neural Networks. Transactions on Machine Learning Research.

Christian Covington (2022). Unbiased Statistical Estimation and Valid Confidence Intervals Under Differential Privacy.

Clément Canonne, Ayush Jain, Gautam, Kamath, Jerry Li (2022). The Price of Tolerance in Distribution Testing. Proceedings of the 35th Annual Conference on Learning Theory (COLT 2022).

Clément L. Canonne, Gautam Kamath, Thomas Steinke (2022). The Discrete Gaussian for Differential Privacy. Journal of Privacy and Confidentiality.

Jayadev Acharya, Ayush Jain, Gautam Kamath, Ananda Theertha Suresh, Huanyu Zhang (2022). Robust Estimation for Random Graphs. Proceedings of the 35th Annual Conference on Learning Theory (COLT 2022).

Gautam Kamath, Xingtu Liu, Huanyu Zhang (2022). Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data. Proceedings of the 39th International Conference on Machine Learning (ICML 2022).

Gautam Kamath, Argyris Mouzakis, Vikrant Singhal, Thomas Steinke, Jonathan Ullman (2022). A Private and Computationally-Efficient Estimator for Unbounded Gaussians. Proceedings of the 35th Annual Conference on Learning Theory (COLT 2022).

Samuel B Hopkins, Gautam Kamath, Mahbod Majid (2022). Efficient Mean Estimation with Pure Differential Privacy via a Sum-of-Squares Exponential Mechanism. Proceedings of the 54th Annual ACM Symposium on the Theory of Computing (STOC 2022).

Da Yu, Saurabh Naik, Arturs Backurs, Sivakanth Gopi, Huseyin A Inan, Gautam Kamath, Janardhan Kulkarni, Yin Tat Lee, Andre Manoel, Lukas Wutschitz, Sergey Yekhanin, Huishuai Zhang (2022). Differentially Private Fine-tuning of Language Models. Proceedings of the 10th International Conference on Learning Representations (ICLR 2022).

Shubhankar Mohapatra, Sajin Sasy, Xi He, Gautam Kamath, Om Thakkar (2022). The Role of Adaptive Optimizers for Honest Private Hyperparameter Selection. Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI 2022).

Ayush Sekhari, Jayadev Acharya, Gautam Kamath, Ananda Theertha Suresh (2021). Remember What You Want to Forget: Algorithms for Machine Unlearning. Advances in Neural Information Processing Systems 34 (NeurIPS 2021).

Pranav Subramani, Nicholas Vadivelu, Gautam Kamath (2021). Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization. Advances in Neural Information Processing Systems 34 (NeurIPS 2021).

Tianshi Cao, Alex Bie, Arash Vahdat, Sanja Fidler, Karsten Kreis (2021). Don’t Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence. Advances in Neural Information Processing Systems 34 (NeurIPS 2021).

Wanrong Zhang, Gautam Kamath, Rachel Cummings (2021). PAPRIKA: Private Online False Discovery Rate Control. Proceedings of the 38th International Conference on Machine Learning (ICML 2021).

Ilias Diakonikolas, Gautam Kamath, Daniel M. Kane, Jerry Li, Ankur Moitra, Alistair Stewart (2021). Robustness Meets Algorithms. Communications of the ACM.

Mark Bun, Gautam Kamath, Thomas Steinke, Zhiwei Steven Wu (2021). Private Hypothesis Selection. IEEE Transactions on Information Theory.

Ishaq Aden-Ali, Hassan Ashtiani, Gautam Kamath (2021). On the Sample Complexity of Privately Learning Unbounded High-Dimensional Gaussians. Proceedings of the 32nd International Conference on Algorithmic Learning Theory (ALT 2021).

Clément L. Canonne, Xi Chen, Gautam Kamath, Amit Levi, Erik Waingarten (2021). Random Restrictions of High-Dimensional Distributions and Uniformity Testing with Subcube Conditioning. Proceedings of the 32nd Annual ACM-SIAM Symposium on Discrete Algorithms (SODA 2021).

Clément L. Canonne, Gautam Kamath, Thomas Steinke (2020). The Discrete Gaussian for Differential Privacy. Advances in Neural Information Processing Systems 33 (NeurIPS 2020).

Clément L. Canonne, Gautam Kamath, Audra McMillan, Jonathan Ullman, Lydia Zakynthinou (2020). Private Identity Testing for High-Dimensional Distributions. Advances in Neural Information Processing Systems 33 (NeurIPS 2020).

Sourav Biswas, Yihe Dong, Gautam Kamath, Jonathan Ullman (2020). CoinPress: Practical Private Mean and Covariance Estimation. Advances in Neural Information Processing Systems 33 (NeurIPS 2020).

Huanyu Zhang, Gautam Kamath, Janardhan Kulkarni, Zhiwei Steven Wu (2020). Privately Learning Markov Random Fields. Proceedings of the 37th International Conference on Machine Learning (ICML 2020).

Gautam Kamath, Vikrant Singhal, Jonathan Ullman (2020). Private Mean Estimation of Heavy-Tailed Distributions. Proceedings of the 33rd Annual Conference on Learning Theory (COLT 2020).

Sivakanth Gopi, Gautam Kamath, Janardhan Kulkarni, Aleksandar Nikolov, Zhiwei Steven Wu, Huanyu Zhang (2020). Locally Private Hypothesis Selection. Proceedings of the 33rd Annual Conference on Learning Theory (COLT 2020).

Jayadev Acharya, Gautam Kamath, Ziteng Sun, Huanyu Zhang (2020). INSPECTRE: Privately Estimating the Unseen. Journal of Privacy and Confidentiality.

Gautam Kamath, Jonathan Ullman (2020). A Primer on Private Statistics. arXiv preprint arXiv:2005.00010.

Mark Bun, Gautam Kamath, Thomas Steinke, Zhiwei Steven Wu (2019). Private Hypothesis Selection. Advances in Neural Information Processing Systems 32 (NeurIPS 2019).

Gautam Kamath, Or Sheffet, Vikrant Singhal, Jonathan Ullman (2019). Differentially Private Algorithms for Learning Mixtures of Separated Gaussians. Advances in Neural Information Processing Systems 32 (NeurIPS 2019).

Constantinos Daskalakis, Nishanth Dikkala, Gautam Kamath (2019). Testing Ising Models. IEEE Transactions on Information Theory.

Clément L. Canonne, Gautam Kamath, Audra McMillan, Adam Smith, Jonathan Ullman (2019). The Structure of Optimal Private Tests for Simple Hypotheses. Proceedings of the 51st Annual ACM Symposium on the Theory of Computing (STOC 2019).

Ilias Diakonikolas, Gautam Kamath, Daniel M. Kane, Jerry Li, Jacob Steinhardt, Alistair Stewart (2019). Sever: A Robust Meta-Algorithm for Stochastic Optimization. Proceedings of the 36th International Conference on Machine Learning (ICML 2019).

Gautam Kamath, Jerry Li, Vikrant Singhal, Jonathan Ullman (2019). Privately Learning High-Dimensional Distributions. Proceedings of the 32nd Annual Conference on Learning Theory (COLT 2019).

Ilias Diakonikolas, Gautam Kamath, Daniel M. Kane, Jerry Li, Ankur Moitra, Alistair Stewart (2019). Robust Estimators in High-Dimensions Without the Computational Intractability. SIAM Journal on Computing.

Gautam Kamath, Christos Tzamos (2019). Anaconda: A Non-Adaptive Conditional Sampling Algorithm for Distribution Testing. Proceedings of the 30th Annual ACM-SIAM Symposium on Discrete Algorithms (SODA 2019).

Jayadev Acharya, Clément L. Canonne, Gautam Kamath (2018). A Chasm Between Identity and Equivalence Testing with Conditional Queries. Theory of Computing.

Gautam Kamath (2018). Modern Challenges in Distribution Testing.

Jayadev Acharya, Gautam Kamath, Ziteng Sun, Huanyu Zhang (2018). INSPECTRE: Privately Estimating the Unseen. Proceedings of the 35th International Conference on Machine Learning (ICML 2018).

Steve Hanneke, Adam Kalai, Gautam Kamath, Christos Tzamos (2018). Actively Avoiding Nonsense in Generative Models. Proceedings of the 31st Annual Conference on Learning Theory (COLT 2018).

Constantinos Daskalakis, Gautam Kamath, John Wright (2018). Which Distribution Distances are Sublinearly Testable?. Proceedings of the 29th Annual ACM-SIAM Symposium on Discrete Algorithms (SODA 2018).

Constantinos Daskalakis, Nishanth Dikkala, Gautam Kamath (2018). Testing Ising Models. Proceedings of the 29th Annual ACM-SIAM Symposium on Discrete Algorithms (SODA 2018).

Ilias Diakonikolas, Gautam Kamath, Daniel M. Kane, Jerry Li, Ankur Moitra, Alistair Stewart (2018). Robustly Learning a Gaussian: Getting Optimal Error, Efficiently. Proceedings of the 29th Annual ACM-SIAM Symposium on Discrete Algorithms (SODA 2018).

Constantinos Daskalakis, Nishanth Dikkala, Gautam Kamath (2017). Concentration of Multilinear Functions of the Ising Model with Applications to Network Data. Advances in Neural Information Processing Systems 30 (NIPS 2017).

Bryan Cai, Constantinos Daskalakis, Gautam Kamath (2017). Priv'IT: Private and Sample Efficient Identity Testing. Proceedings of the 34th International Conference on Machine Learning (ICML 2017).

Ilias Diakonikolas, Gautam Kamath, Daniel M. Kane, Jerry Li, Ankur Moitra, Alistair Stewart (2017). Being Robust (in High Dimensions) Can Be Practical. Proceedings of the 34th International Conference on Machine Learning (ICML 2017).

Ilias Diakonikolas, Gautam Kamath, Daniel M. Kane, Jerry Li, Ankur Moitra, Alistair Stewart (2016). Robust Estimators in High Dimensions without the Computational Intractability. Proceedings of the 57th Annual IEEE Symposium on Foundations of Computer Science (FOCS 2016).

Constantinos Daskalakis, Anindya De, Gautam Kamath, Christos Tzamos (2016). A Size-Free CLT for Poisson Multinomials and its Applications. Proceedings of the 48th Annual ACM Symposium on the Theory of Computing (STOC 2016).

Jayadev Acharya, Constantinos Daskalakis, Gautam Kamath (2015). Optimal Testing for Properties of Distributions. Advances in Neural Information Processing Systems 28 (NIPS 2015).

Constantinos Daskalakis, Gautam Kamath, Christos Tzamos (2015). On the Structure, Covering, and Learning of Poisson Multinomial Distributions. Proceedings of the 56th Annual IEEE Symposium on Foundations of Computer Science (FOCS 2015).

Jayadev Acharya, Clément L. Canonne, Gautam Kamath (2015). A Chasm Between Identity and Equivalence Testing with Conditional Queries. Proceedings of the 19th International Workshop of Randomization and Computation (RANDOM 2015).

Jayadev Acharya, Clément L. Canonne, Gautam Kamath (2015). Adaptive Estimation in Weighted Group Testing. Proceedings of the 2015 IEEE International Symposium on Information Theory (ISIT 2015).

Gautam Kamath (2014). On Learning and Covering Structured Distributions.

Constantinos Daskalakis, Gautam Kamath (2014). Faster and Sample Near-Optimal Algorithms for Proper Learning Mixtures of Gaussians. Proceedings of the 27th Annual Conference on Learning Theory (COLT 2014).

Christina Brandt, Nicole Immorlica, Gautam Kamath, Robert Kleinberg (2012). An Analysis of One-Dimensional Schelling Segregation. Proceedings of the 44th Annual ACM Symposium on the Theory of Computing (STOC 2012).