Gautam Kamath

Demystifying Foreground-Background Memorization in Diffusion Models AAAI 2026 Algorithmic Learning Theory 2025: Preface ALT 2025 Machine Unlearning Fails to Remove Data Poisoning Attacks ICLR 2025 On the Learnability of Distribution Classes with Adaptive Adversaries ICML 2025 Optimal Differentially Private Sampling of Unbounded Gaussians COLT 2025 Differentially Private Post-Processing for Fair Regression ICML 2024 Disguised Copyright Infringement of Latent Diffusion Models ICML 2024 Not All Learnable Distribution Classes are Privately Learnable ALT 2024 Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining ICML 2024 Distribution Learnability and Robustness NeurIPS 2023 Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks ICML 2023 Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks NeurIPS 2023 Private Distribution Learning with Public Data: The View from Sample Compression NeurIPS 2023 A Private and Computationally-Efficient Estimator for Unbounded Gaussians COLT 2022 Differentially Private Fine-tuning of Language Models ICLR 2022 Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data ICML 2022 New Lower Bounds for Private Estimation and a Generalized Fingerprinting Lemma NeurIPS 2022 Private Estimation with Public Data NeurIPS 2022 Robust Estimation for Random Graphs COLT 2022 The Price of Tolerance in Distribution Testing COLT 2022 The Role of Adaptive Optimizers for Honest Private Hyperparameter Selection AAAI 2022 Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization NeurIPS 2021 On the Sample Complexity of Privately Learning Unbounded High-Dimensional Gaussians ALT 2021 PAPRIKA: Private Online False Discovery Rate Control ICML 2021 Remember What You Want to Forget: Algorithms for Machine Unlearning NeurIPS 2021 CoinPress: Practical Private Mean and Covariance Estimation NeurIPS 2020 Locally Private Hypothesis Selection COLT 2020 Private Identity Testing for High-Dimensional Distributions NeurIPS 2020 Privately Learning Markov Random Fields ICML 2020 Private Mean Estimation of Heavy-Tailed Distributions COLT 2020 The Discrete Gaussian for Differential Privacy NeurIPS 2020 Differentially Private Algorithms for Learning Mixtures of Separated Gaussians NeurIPS 2019 Private Hypothesis Selection NeurIPS 2019 Privately Learning High-Dimensional Distributions COLT 2019 Sever: A Robust Meta-Algorithm for Stochastic Optimization ICML 2019 Actively Avoiding Nonsense in Generative Models COLT 2018 INSPECTRE: Privately Estimating the Unseen ICML 2018 Being Robust (in High Dimensions) Can Be Practical ICML 2017 Concentration of Multilinear Functions of the Ising Model with Applications to Network Data NeurIPS 2017 Priv’IT: Private and Sample Efficient Identity Testing ICML 2017 Optimal Testing for Properties of Distributions NeurIPS 2015 Faster and Sample Near-Optimal Algorithms for Proper Learning Mixtures of Gaussians COLT 2014