Abhradeep Guha Thakurta

40 papers A* 21A 1B 1Journal 15Unranked 2

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy. CoRR Vishnu Vinod, Krishna Pillutla, Abhradeep Guha Thakurta
2025	A*	`conf`	Near-Exact Privacy Amplification for Matrix Mechanisms. ICLR Christopher A. Choquette-Choo, Arun Ganesh, Saminul Haque, Thomas Steinke, Abhradeep Guha Thakurta
2025	B	`conf`	Near-Optimal Rates for O(1)-Smooth DP-SCO with a Single Epoch and Large Batches. ALT Christopher A. Choquette-Choo, Arun Ganesh, Abhradeep Guha Thakurta
2025	J	`jnl`	Preserving Expert-Level Privacy in Offline Reinforcement Learning. Trans. Mach. Learn. Res. Navodita Sharma, Vishnu Vinod, Abhradeep Guha Thakurta, Alekh Agarwal, Borja Balle, Christoph Dann, Aravindan Raghuveer
2025	A*	`conf`	The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD. ICLR Milad Nasr, Thomas Steinke, Borja Balle, Christopher A. Choquette-Choo, Arun Ganesh, Matthew Jagielski, Jamie Hayes, Abhradeep Guha Thakurta, Adam Smith, Andreas Terzis
2024	A*	`conf`	Correlated Noise Provably Beats Independent Noise for Differentially Private Learning. ICLR Christopher A. Choquette-Choo, Krishnamurthy Dj Dvijotham, Krishna Pillutla, Arun Ganesh, Thomas Steinke, Abhradeep Guha Thakurta
2024	A*	`conf`	Improved Differentially Private and Lazy Online Convex Optimization: Lower Regret without Smoothness Requirements. ICML Naman Agarwal, Satyen Kale, Karan Singh, Abhradeep Guha Thakurta
2024	A*	`conf`	Privacy Amplification for Matrix Mechanisms. ICLR Christopher A. Choquette-Choo, Arun Ganesh, Thomas Steinke, Abhradeep Guha Thakurta
2024	A*	`conf`	Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation. ICML Gavin Brown, Krishnamurthy Dj Dvijotham, Georgina Evans, Daogao Liu, Adam Smith, Abhradeep Guha Thakurta
2024	J	`jnl`	The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD. CoRR Thomas Steinke, Milad Nasr, Arun Ganesh, Borja Balle, Christopher A. Choquette-Choo, Matthew Jagielski, Jamie Hayes, Abhradeep Guha Thakurta, Adam Smith, Andreas Terzis
2023	A*	`conf`	(Amplified) Banded Matrix Factorization: A unified approach to private training. NeurIPS Christopher A. Choquette-Choo, Arun Ganesh, Ryan McKenna, H. Brendan McMahan, John Rush, Abhradeep Guha Thakurta, Zheng Xu
2023	J	`jnl`	(Amplified) Banded Matrix Factorization: A unified approach to private training. CoRR Christopher A. Choquette-Choo, Arun Ganesh, Ryan McKenna, H. Brendan McMahan, Keith Rush, Abhradeep Guha Thakurta, Zheng Xu
2023	J	`jnl`	Differentially Private Image Classification from Features. Trans. Mach. Learn. Res. Harsh Mehta, Walid Krichene, Abhradeep Guha Thakurta, Alexey Kurakin, Ashok Cutkosky
2023	A*	`conf`	Faster Differentially Private Convex Optimization via Second-Order Methods. NeurIPS Arun Ganesh, Mahdi Haghifam, Thomas Steinke, Abhradeep Guha Thakurta
2023	J	`jnl`	How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy. J. Artif. Intell. Res. Natalia Ponomareva, Hussein Hazimeh, Alex Kurakin, Zheng Xu, Carson Denison, H. Brendan McMahan, Sergei Vassilvitskii, Steve Chien, Abhradeep Guha Thakurta
2023	J	`jnl`	Improved Differentially Private and Lazy Online Convex Optimization. CoRR Naman Agarwal, Satyen Kale, Karan Singh, Abhradeep Guha Thakurta
2023	A*	`conf`	Measuring Forgetting of Memorized Training Examples. ICLR Matthew Jagielski, Om Thakkar, Florian Tramèr, Daphne Ippolito, Katherine Lee, Nicholas Carlini, Eric Wallace, Shuang Song, Abhradeep Guha Thakurta, Nicolas Papernot, Chiyuan Zhang
2023	A*	`conf`	Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learning. ICML Christopher A. Choquette-Choo, Hugh Brendan McMahan, J. Keith Rush, Abhradeep Guha Thakurta
2023	A*	`conf`	Multi-Task Differential Privacy Under Distribution Skew. ICML Walid Krichene, Prateek Jain, Shuang Song, Mukund Sundararajan, Abhradeep Guha Thakurta, Li Zhang
2023	A*	`conf`	Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks. NeurIPS Daogao Liu, Arun Ganesh, Sewoong Oh, Abhradeep Guha Thakurta
2023	J	`jnl`	Towards Large Scale Transfer Learning for Differentially Private Image Classification. Trans. Mach. Learn. Res. Harsh Mehta, Abhradeep Guha Thakurta, Alexey Kurakin, Ashok Cutkosky
2023	A*	`conf`	Training Private Models That Know What They Don't Know. NeurIPS Stephan Rabanser, Anvith Thudi, Abhradeep Guha Thakurta, Krishnamurthy Dvijotham, Nicolas Papernot
2023	A*	`conf`	Why Is Public Pretraining Necessary for Private Model Training? ICML Arun Ganesh, Mahdi Haghifam, Milad Nasr, Sewoong Oh, Thomas Steinke, Om Thakkar, Abhradeep Guha Thakurta, Lun Wang
2022	A*	`conf`	Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams. NeurIPS Sergey Denisov, H. Brendan McMahan, John Rush, Adam D. Smith, Abhradeep Guha Thakurta
2022	J	`jnl`	Private Matrix Approximation and Geometry of Unitary Orbits. CoRR Oren Mangoubi, Yikai Wu, Satyen Kale, Abhradeep Guha Thakurta, Nisheeth K. Vishnoi
2022	J	`jnl`	Private Online Prefix Sums via Optimal Matrix Factorizations. CoRR Brendan McMahan, Keith Rush, Abhradeep Guha Thakurta
2022	J	`jnl`	Private and Efficient Meta-Learning with Low Rank and Sparse Decomposition. CoRR Soumyabrata Pal, Prateek Varshney, Prateek Jain, Abhradeep Guha Thakurta, Gagan Madan, Gaurav Aggarwal, Pradeep Shenoy, Gaurav Srivastava
2022	A*	`conf`	When Does Differentially Private Learning Not Suffer in High Dimensions? NeurIPS Xuechen Li, Daogao Liu, Tatsunori B. Hashimoto, Huseyin A. Inan, Janardhan Kulkarni, Yin Tat Lee, Abhradeep Guha Thakurta
2022	J	`jnl`	When Does Differentially Private Learning Not Suffer in High Dimensions? CoRR Xuechen Li, Daogao Liu, Tatsunori Hashimoto, Huseyin A. Inan, Janardhan Kulkarni, Yin Tat Lee, Abhradeep Guha Thakurta
2021	A*	`conf`	A Separation Result Between Data-oblivious and Data-aware Poisoning Attacks. NeurIPS Samuel Deng, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Abhradeep Guha Thakurta
2021	A*	`conf`	Differentially Private Model Personalization. NeurIPS Prateek Jain, John Rush, Adam D. Smith, Shuang Song, Abhradeep Guha Thakurta
2021	J	`jnl`	Node-Level Differentially Private Graph Neural Networks. CoRR Ameya Daigavane, Gagan Madan, Aditya Sinha, Abhradeep Guha Thakurta, Gaurav Aggarwal, Prateek Jain
2019	A	`conf`	Privacy-preserving Data Mining in Industry. WSDM Krishnaram Kenthapadi, Ilya Mironov, Abhradeep Guha Thakurta
2019	A*	`conf`	Private Stochastic Convex Optimization with Optimal Rates. NeurIPS Raef Bassily, Vitaly Feldman, Kunal Talwar, Abhradeep Guha Thakurta
2018	A*	`conf`	Model-Agnostic Private Learning. NeurIPS Raef Bassily, Abhradeep Guha Thakurta, Om Dipakbhai Thakkar
2017	—	`conf`	Practical Locally Private Heavy Hitters. NIPS Raef Bassily, Kobbi Nissim, Uri Stemmer, Abhradeep Guha Thakurta
2014	A*	`conf`	(Near) Dimension Independent Risk Bounds for Differentially Private Learning. ICML Prateek Jain, Abhradeep Guha Thakurta
2013	—	`conf`	(Nearly) Optimal Algorithms for Private Online Learning in Full-information and Bandit Settings. NIPS Abhradeep Guha Thakurta, Adam D. Smith
2007	J	`jnl`	English Speech to Skanskrit Speech Translator. Res. Comput. Sci. Abhradeep Guha Thakurta, Ashwath Kumar, Hashir Khan
2006	J	`jnl`	GRASP Approach for the Glass Cutting Problem. Res. Comput. Sci. Abhradeep Guha Thakurta, Ashwath Kumar, Vijayan Immanuel