Publications by Group Members

(2025). Private Mean Estimation with Person-Level Differential Privacy. Proceedings of the 36th Annual ACM-SIAM Symposium on Discrete Algorithms (SODA 2025).

PDF

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

PDF

(2024). Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data. arXiv preprint arXiv:2409.19798.

PDF

(2024). Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining. Proceedings of the 41st International Conference on Machine Learning (ICML 2024).

PDF

(2024). Disguised Copyright Infringement of Latent Diffusion Models. Proceedings of the 41st International Conference on Machine Learning (ICML 2024).

PDF

(2024). Differentially Private Post-Processing for Fair Regression. Proceedings of the 41st International Conference on Machine Learning (ICML 2024).

PDF

(2024). Machine Unlearning Fails to Remove Data Poisoning Attacks. arXiv preprint arXiv:2406.17216.

PDF

(2024). Differentially Private Fine-tuning of Language Models. Journal of Privacy and Confidentiality.

PDF

(2024). Avoiding Pitfalls for Privacy Accounting of Subsampled Mechanisms under Composition. arXiv preprint arXiv:2405.20769.

PDF

(2024). Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors. Proceedings of the 2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML 2024).

PDF

(2024). Not All Learnable Distribution Classes are Privately Learnable. Proceedings of the 35th International Conference on Algorithmic Learning Theory (ALT 2024).

PDF

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

PDF

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

PDF

(2024). Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment. Harvard Data Science Review.

PDF

(2023). Private Distribution Learning with Public Data: The View from Sample Compression. Advances in Neural Information Processing Systems 36 (NeurIPS 2023).

PDF

(2023). Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks. Advances in Neural Information Processing Systems 36 (NeurIPS 2023).

PDF

(2023). Distribution Learnability and Robustness. Advances in Neural Information Processing Systems 36 (NeurIPS 2023).

PDF

(2023). Report of the 1st Workshop on Generative AI and Law. arXiv preprint arXiv:2311.06477.

PDF

(2023). Private GANs, Revisited. Transactions on Machine Learning Research.

PDF

(2023). Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent. Transactions on Machine Learning Research.

PDF

(2023). Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks. Proceedings of the 40th International Conference on Machine Learning (ICML 2023).

PDF

(2023). Robustness Implies Privacy in Statistical Estimation. Proceedings of the 55th Annual ACM Symposium on the Theory of Computing (STOC 2023).

PDF

(2023). Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance. arXiv preprint arXiv:2303.01256.

PDF

(2023). A Bias-Variance-Privacy Trilemma for Statistical Estimation. arXiv preprint arXiv:2301.13334.

PDF

(2022). Private Estimation with Public Data. Advances in Neural Information Processing Systems 35 (NeurIPS 2022).

PDF

(2022). New Lower Bounds for Private Estimation and a Generalized Fingerprinting Lemma. Advances in Neural Information Processing Systems 35 (NeurIPS 2022).

PDF

(2022). Indiscriminate Data Poisoning Attacks on Neural Networks. Transactions on Machine Learning Research.

PDF

(2022). The Price of Tolerance in Distribution Testing. Proceedings of the 35th Annual Conference on Learning Theory (COLT 2022).

PDF

(2022). The Discrete Gaussian for Differential Privacy. Journal of Privacy and Confidentiality.

PDF

(2022). Robust Estimation for Random Graphs. Proceedings of the 35th Annual Conference on Learning Theory (COLT 2022).

PDF

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

PDF

(2022). A Private and Computationally-Efficient Estimator for Unbounded Gaussians. Proceedings of the 35th Annual Conference on Learning Theory (COLT 2022).

PDF

(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).

PDF

(2022). Differentially Private Fine-tuning of Language Models. Proceedings of the 10th International Conference on Learning Representations (ICLR 2022).

PDF

(2022). The Role of Adaptive Optimizers for Honest Private Hyperparameter Selection. Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI 2022).

PDF

(2021). Remember What You Want to Forget: Algorithms for Machine Unlearning. Advances in Neural Information Processing Systems 34 (NeurIPS 2021).

PDF

(2021). Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization. Advances in Neural Information Processing Systems 34 (NeurIPS 2021).

PDF

(2021). Don’t Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence. Advances in Neural Information Processing Systems 34 (NeurIPS 2021).

PDF

(2021). Unbiased Statistical Estimation and Valid Confidence Intervals Under Differential Privacy. arXiv preprint arXiv:2110.14465.

PDF

(2021). PAPRIKA: Private Online False Discovery Rate Control. Proceedings of the 38th International Conference on Machine Learning (ICML 2021).

PDF

(2021). Robustness Meets Algorithms. Communications of the ACM.

PDF

(2021). On the Sample Complexity of Privately Learning Unbounded High-Dimensional Gaussians. Proceedings of the 32nd International Conference on Algorithmic Learning Theory (ALT 2021).

PDF

(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).

PDF

(2021). Private Hypothesis Selection. IEEE Transactions on Information Theory.

PDF

(2020). The Discrete Gaussian for Differential Privacy. Advances in Neural Information Processing Systems 33 (NeurIPS 2020).

PDF

(2020). Private Identity Testing for High-Dimensional Distributions. Advances in Neural Information Processing Systems 33 (NeurIPS 2020).

PDF

(2020). CoinPress: Practical Private Mean and Covariance Estimation. Advances in Neural Information Processing Systems 33 (NeurIPS 2020).

PDF

(2020). Privately Learning Markov Random Fields. Proceedings of the 37th International Conference on Machine Learning (ICML 2020).

PDF

(2020). Private Mean Estimation of Heavy-Tailed Distributions. Proceedings of the 33rd Annual Conference on Learning Theory (COLT 2020).

PDF

(2020). Locally Private Hypothesis Selection. Proceedings of the 33rd Annual Conference on Learning Theory (COLT 2020).

PDF

(2020). INSPECTRE: Privately Estimating the Unseen. Journal of Privacy and Confidentiality.

PDF

(2020). A Primer on Private Statistics. arXiv preprint arXiv:2005.00010.

PDF

(2019). Private Hypothesis Selection. Advances in Neural Information Processing Systems 32 (NeurIPS 2019).

PDF

(2019). Differentially Private Algorithms for Learning Mixtures of Separated Gaussians. Advances in Neural Information Processing Systems 32 (NeurIPS 2019).

PDF

(2019). Testing Ising Models. IEEE Transactions on Information Theory.

PDF

(2019). The Structure of Optimal Private Tests for Simple Hypotheses. Proceedings of the 51st Annual ACM Symposium on the Theory of Computing (STOC 2019).

PDF

(2019). Sever: A Robust Meta-Algorithm for Stochastic Optimization. Proceedings of the 36th International Conference on Machine Learning (ICML 2019).

PDF

(2019). Privately Learning High-Dimensional Distributions. Proceedings of the 32nd Annual Conference on Learning Theory (COLT 2019).

PDF

(2019). Robust Estimators in High-Dimensions Without the Computational Intractability. SIAM Journal on Computing.

PDF

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

PDF

(2018). A Chasm Between Identity and Equivalence Testing with Conditional Queries. Theory of Computing.

PDF

(2018). INSPECTRE: Privately Estimating the Unseen. Proceedings of the 35th International Conference on Machine Learning (ICML 2018).

PDF

(2018). Actively Avoiding Nonsense in Generative Models. Proceedings of the 31st Annual Conference on Learning Theory (COLT 2018).

PDF

(2018). Which Distribution Distances are Sublinearly Testable?. Proceedings of the 29th Annual ACM-SIAM Symposium on Discrete Algorithms (SODA 2018).

PDF

(2018). Testing Ising Models. Proceedings of the 29th Annual ACM-SIAM Symposium on Discrete Algorithms (SODA 2018).

PDF

(2018). Robustly Learning a Gaussian: Getting Optimal Error, Efficiently. Proceedings of the 29th Annual ACM-SIAM Symposium on Discrete Algorithms (SODA 2018).

PDF

(2017). Concentration of Multilinear Functions of the Ising Model with Applications to Network Data. Advances in Neural Information Processing Systems 30 (NIPS 2017).

PDF

(2017). Priv'IT: Private and Sample Efficient Identity Testing. Proceedings of the 34th International Conference on Machine Learning (ICML 2017).

PDF

(2017). Being Robust (in High Dimensions) Can Be Practical. Proceedings of the 34th International Conference on Machine Learning (ICML 2017).

PDF

(2016). Robust Estimators in High Dimensions without the Computational Intractability. Proceedings of the 57th Annual IEEE Symposium on Foundations of Computer Science (FOCS 2016).

PDF

(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).

PDF

(2015). Optimal Testing for Properties of Distributions. Advances in Neural Information Processing Systems 28 (NIPS 2015).

PDF

(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).

PDF

(2015). A Chasm Between Identity and Equivalence Testing with Conditional Queries. Proceedings of the 19th International Workshop of Randomization and Computation (RANDOM 2015).

PDF

(2015). Adaptive Estimation in Weighted Group Testing. Proceedings of the 2015 IEEE International Symposium on Information Theory (ISIT 2015).

PDF

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

PDF

(2012). An Analysis of One-Dimensional Schelling Segregation. Proceedings of the 44th Annual ACM Symposium on the Theory of Computing (STOC 2012).

PDF