GK
Gautam Kamath
cs.LGcs.CRcs.DSstat.MLcs.ITmath.ITmath.STstat.THmath.PRcs.AI
On Valency
published · living versionsW_5m2zmfqb·v1 · currentpublished
Efficient and Optimal Learning of Discrete Distributions with Person-Level Privacy
with Mahbod Majid, Ankur Moitra, Argyris Mouzakis, Jonathan Ullman
1 version
W_ev86av6e·v1published
Preprints & journals
81 papers in the corpus · 2012–2026Actually, All Learnable Distribution Classes Are Privately Learnable2610.28878v1 · Mohammad Afzali, Hassan Ashtiani, Alex Bie et al.2026 · 0 citationsarXivon Valency
Tight Bounds for Equivalence Testing with Non-Adaptive Conditional Samples2610.11145v1 · Gautam Kamath2026 · 0 citationsarXiv
Revisiting the Provable-Auditable Privacy Gap of DP-SGD2608.28934v1 · Saloni Modi, Srivi Balaji, Yusong Zhu et al.2026 · 0 citationsarXiv
Sequential Data Poisoning in LLM Post-Training2606.04929v1 · Jack Sanderson, Yihan Wang, Xiaoqian Lu et al.2026 · 0 citationsarXiv
Near-Optimal Machine Unlearning Utility for Smooth Strongly Convex Losses2606.01527v2 · Matthew Regehr, Gautam Kamath, Andrew Lowy2026 · 0 citationsarXiv
ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?2606.01849v2 · Peihan Liu, Lucas Rosenblatt, Weiwei Kong et al.2026 · 0 citationsarXiv
Robust Statistical Estimators with Bounded Empirical Sensitivity2605.21860v1 · Valentio Iverson, Gautam Kamath, Argyris Mouzakis et al.2026 · 0 citationsarXiv
DriftXpress: Faster Drifting Models via Projected RKHS Fields2605.12183v2 · Ali Falahati, Elliot Creager, Gautam Kamath et al.2026 · 0 citationsarXiv
Rethinking Benchmarks for Differentially Private Image Classification2601.17189v2 · Sabrina Mokhtari, Sara Kodeiri, Shubhankar Mohapatra et al.2026 · 0 citationsIEEE Technical Committee on Data Engineering 2025
Query-Efficient Locally Private Hypothesis Selection via the Scheffe Graph2509.16180v2 · Gautam Kamath, Alireza F. Pour, Matthew Regehr et al.2025 · 0 citationsarXiv
Are Targeted Data Poisoning Attacks as Effective as We Think?2509.06896v3 · William Xu, Chenyu Zhang, Yihan Wang et al.2025 · 0 citationsarXiv
On the Learnability of Distribution Classes with Adaptive Adversaries2509.05137v1 · Tosca Lechner, Alex Bie, Gautam Kamath2025 · 0 citationsarXiv
Demystifying Foreground-Background Memorization in Diffusion Models2508.12148v1 · Jimmy Z. Di, Yiwei Lu, Yaoliang Yu et al.2025 · 0 citationsarXiv
Optimal Differentially Private Sampling of Unbounded Gaussians2503.01766v1 · Valentio Iverson, Gautam Kamath, Argyris Mouzakis2025 · 0 citationsarXiv
BridgePure: Limited Protection Leakage Can Break Black-Box Data Protection2412.21061v2 · Yihan Wang, Yiwei Lu, Xiao-Shan Gao et al.2024 · 0 citationsarXiv
The Broader Landscape of Robustness in Algorithmic Statistics2412.02670v3 · Gautam Kamath2024 · 0 citationsarXiv
Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data2409.19798v2 · Jie Zhang, Debeshee Das, Gautam Kamath et al.2024 · 2 citationsarXiv
Machine Unlearning Fails to Remove Data Poisoning Attacks2406.17216v3 · Martin Pawelczyk, Jimmy Z. Di, Yiwei Lu et al.2024 · 0 citationsarXiv
Distribution Learnability and Robustness2406.17814v1 · Shai Ben-David, Alex Bie, Gautam Kamath et al.2024 · 1 citationarXiv
Private Mean Estimation with Person-Level Differential Privacy2405.20405v3 · Sushant Agarwal, Gautam Kamath, Mahbod Majid et al.2024 · 6 citationsarXiv
Avoiding Pitfalls for Privacy Accounting of Subsampled Mechanisms under Composition2405.20769v2 · Christian Janos Lebeda, Matthew Regehr, Gautam Kamath et al.2024 · 1 citationarXiv
Differentially Private Post-Processing for Fair Regression2405.04034v1 · Ruicheng Xian, Qiaobo Li, Gautam Kamath et al.2024 · 1 citationarXiv
Disguised Copyright Infringement of Latent Diffusion Models2404.06737v4 · Yiwei Lu, Matthew Y.R. Yang, Zuoqiu Liu et al.2024 · 0 citationsarXiv
Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors2402.12626v1 · Yiwei Lu, Matthew Y.R. Yang, Gautam Kamath et al.2024 · 5 citationsarXiv
Not All Learnable Distribution Classes are Privately Learnable2402.00267v4 · Mark Bun, Gautam Kamath, Argyris Mouzakis et al.2024 · 0 citationsarXiv
Report of the 1st Workshop on Generative AI and Law2311.06477v3 · A. Feder Cooper, Katherine Lee, James Grimmelmann et al.2023 · 6 citationsarXiv
Private Distribution Learning with Public Data: The View from Sample Compression2308.06239v2 · Shai Ben-David, Alex Bie, Cl'ement L. Canonne et al.2023 · 1 citationarXiv
Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment2304.06929v2 · Rachel Cummings, Damien Desfontaines, David Evans et al.2023 · 52 citationsarXiv
Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks2303.03592v3 · Yiwei Lu, Gautam Kamath, Yaoliang Yu2023 · 3 citationsarXiv
Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance2303.01256v2 · Xin Gu, Gautam Kamath, Zhiwei Steven Wu2023 · 3 citationsarXiv
Private GANs, Revisited2302.02936v2 · Alex Bie, Gautam Kamath, Guojun Zhang2023 · 4 citationsarXiv
A Bias-Accuracy-Privacy Trilemma for Statistical Estimation2301.13334v3 · Gautam Kamath, Argyris Mouzakis, Matthew Regehr et al.2023 · 0 citationsarXiv
Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks2212.10717v2 · Jimmy Z. Di, Jack Douglas, Jayadev Acharya et al.2022 · 17 citationsarXiv
Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining2212.06470v3 · Florian Tramer, Gautam Kamath, Nicholas Carlini2022 · 9 citationsarXiv
Robustness Implies Privacy in Statistical Estimation2212.05015v3 · Samuel B. Hopkins, Gautam Kamath, Mahbod Majid et al.2022 · 24 citationsarXiv
Private Estimation with Public Data2208.07984v2 · Alex Bie, Gautam Kamath, Vikrant Singhal2022 · 8 citationsarXiv
Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent2206.02617v7 · Da Yu, Gautam Kamath, Janardhan Kulkarni et al.2022 · 5 citationsarXiv
New Lower Bounds for Private Estimation and a Generalized Fingerprinting Lemma2205.08532v5 · Gautam Kamath, Argyris Mouzakis, Vikrant Singhal2022 · 7 citationsarXiv
Indiscriminate Data Poisoning Attacks on Neural Networks2204.09092v2 · Yiwei Lu, Gautam Kamath, Yaoliang Yu2022 · 7 citationsarXiv
Calibration with Privacy in Peer Review2201.11308v1 · Wenxin Ding, Gautam Kamath, Weina Wang et al.2022 · 3 citationsarXiv
Efficient Mean Estimation with Pure Differential Privacy via a Sum-of-Squares Exponential Mechanism2111.12981v2 · Samuel B. Hopkins, Gautam Kamath, Mahbod Majid2021 · 25 citationsarXiv
The Role of Adaptive Optimizers for Honest Private Hyperparameter Selection2111.04906v1 · Shubhankar Mohapatra, Sajin Sasy, Xi He et al.2021 · 15 citationsarXiv
Robust Estimation for Random Graphs2111.05320v2 · Jayadev Acharya, Ayush Jain, Gautam Kamath et al.2021 · 1 citationarXiv
A Private and Computationally-Efficient Estimator for Unbounded Gaussians2111.04609v2 · Gautam Kamath, Argyris Mouzakis, Vikrant Singhal et al.2021 · 8 citationsarXiv
Unbiased Statistical Estimation and Valid Confidence Intervals Under Differential Privacy2110.14465v2 · Christian Covington, Xi He, James Honaker et al.2021 · 5 citationsarXiv
Differentially Private Fine-tuning of Language Models2110.06500v2 · Da Yu, Saurabh Naik, Arturs Backurs et al.2021 · 101 citationsarXiv
The Price of Tolerance in Distribution Testing2106.13414v2 · Cl'ement L. Canonne, Ayush Jain, Gautam Kamath et al.2021 · 1 citationarXiv
Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data2106.01336v6 · Gautam Kamath, Xingtu Liu, Huanyu Zhang2021 · 11 citationsarXiv
Remember What You Want to Forget: Algorithms for Machine Unlearning2103.03279v2 · Ayush Sekhari, Jayadev Acharya, Gautam Kamath et al.2021 · 99 citationsarXiv
On the Sample Complexity of Privately Learning Unbounded High-Dimensional Gaussians2010.09929v1 · Ishaq Aden-Ali, Hassan Ashtiani, Gautam Kamath2020 · 12 citationsarXiv
Career total: 103 works. 81 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.