Anvith Thudi

30 papers A* 9A 2Journal 19
YearRankTypeTitle / Venue / Authors
2026 J jnl
Gauss-Newton Unlearning for the LLM Era.
CoRR
Lev McKinney, Anvith Thudi, Juhan Bae, Tara Rezaei, Nicolas Papernot, Sheila A. McIlraith, Roger B. Grosse
2025 J jnl
Efficient Public Verification of Private ML via Regularization.
CoRR
Zoë Ruha Bell, Anvith Thudi, Olive Franzese-McLaughlin, Nicolas Papernot, Shafi Goldwasser
2025 A* conf
Fast Exact Unlearning for In-Context Learning Data for LLMs.
ICML
Andrei Ioan Muresanu, Anvith Thudi, Michael R. Zhang, Nicolas Papernot
2025 A* conf
Leveraging Per-Instance Privacy for Machine Unlearning.
ICML
Nazanin Mohammadi Sepahvand, Anvith Thudi, Berivan Isik, Ashmita Bhattacharyya, Nicolas Papernot, Eleni Triantafillou, Daniel M. Roy, Gintare Karolina Dziugaite
2025 J jnl
Leveraging Per-Instance Privacy for Machine Unlearning.
CoRR
Nazanin Mohammadi Sepahvand, Anvith Thudi, Berivan Isik, Ashmita Bhattacharyya, Nicolas Papernot, Eleni Triantafillou, Daniel M. Roy, Gintare Karolina Dziugaite
2025 A* conf
MixMax: Distributional Robustness in Function Space via Optimal Data Mixtures.
ICLR
Anvith Thudi, Chris J. Maddison
2025 A* conf
MixMin: Finding Data Mixtures via Convex Minimization.
ICML
Anvith Thudi, Evianne Rovers, Yangjun Ruan, Tristan Thrush, Chris J. Maddison
2025 J jnl
MixMin: Finding Data Mixtures via Convex Minimization.
CoRR
Anvith Thudi, Evianne Rovers, Yangjun Ruan, Tristan Thrush, Chris J. Maddison
2025 J jnl
Sampling Arbitrary Discrete Distributions for RV Commitment Schemes Using the Trimmed-Tree Knuth-Yao Algorithm.
IACR Cryptol. ePrint Arch.
Zoë Ruha Bell, Anvith Thudi
2025 J jnl
Selective Prediction via Training Dynamics.
Trans. Mach. Learn. Res.
Stephan Rabanser, Anvith Thudi, Kimia Hamidieh, Adam Dziedzic, Israfil Bahceci, Akram Bin Sediq, Hamza Umit Sokun, Nicolas Papernot
2024 A* conf
Better Sparsifiers for Directed Eulerian Graphs.
ICALP
Sushant Sachdeva, Anvith Thudi, Yibin Zhao
2024 J jnl
Finding Optimally Robust Data Mixtures via Concave Maximization.
CoRR
Anvith Thudi, Chris J. Maddison
2024 J jnl
From Differential Privacy to Bounds on Membership Inference: Less can be More.
Trans. Mach. Learn. Res.
Anvith Thudi, Ilia Shumailov, Franziska Boenisch, Nicolas Papernot
2024 A* conf
Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD.
USENIX Security Symposium
Anvith Thudi, Hengrui Jia, Casey Meehan, Ilia Shumailov, Nicolas Papernot
2024 J jnl
Unlearnable Algorithms for In-context Learning.
CoRR
Andrei Ioan Muresanu, Anvith Thudi, Michael R. Zhang, Nicolas Papernot
2023 J jnl
Better Sparsifiers for Directed Eulerian Graphs.
CoRR
Sushant Sachdeva, Anvith Thudi, Yibin Zhao
2023 J jnl
Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD.
CoRR
Anvith Thudi, Hengrui Jia, Casey Meehan, Ilia Shumailov, Nicolas Papernot
2023 A conf
Proof-of-Learning is Currently More Broken Than You Think.
EuroS&P
Congyu Fang, Hengrui Jia, Anvith Thudi, Mohammad Yaghini, Christopher A. Choquette-Choo, Natalie Dullerud, Varun Chandrasekaran, Nicolas Papernot
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 J jnl
Training Private Models That Know What They Don't Know.
CoRR
Stephan Rabanser, Anvith Thudi, Abhradeep Thakurta, Krishnamurthy Dvijotham, Nicolas Papernot
2022 J jnl
Bounding Membership Inference.
CoRR
Anvith Thudi, Ilia Shumailov, Franziska Boenisch, Nicolas Papernot
2022 J jnl
On the Fundamental Limits of Formally (Dis)Proving Robustness in Proof-of-Learning.
CoRR
Congyu Fang, Hengrui Jia, Anvith Thudi, Mohammad Yaghini, Christopher A. Choquette-Choo, Natalie Dullerud, Varun Chandrasekaran, Nicolas Papernot
2022 A* conf
On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning.
USENIX Security Symposium
Anvith Thudi, Hengrui Jia, Ilia Shumailov, Nicolas Papernot
2022 J jnl
Selective Classification Via Neural Network Training Dynamics.
CoRR
Stephan Rabanser, Anvith Thudi, Kimia Hamidieh, Adam Dziedzic, Nicolas Papernot
2022 A conf
Unrolling SGD: Understanding Factors Influencing Machine Unlearning.
EuroS&P
Anvith Thudi, Gabriel Deza, Varun Chandrasekaran, Nicolas Papernot
2021 J jnl
On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning.
CoRR
Anvith Thudi, Hengrui Jia, Ilia Shumailov, Nicolas Papernot
2021 A* conf
Proof-of-Learning: Definitions and Practice.
SP
Hengrui Jia, Mohammad Yaghini, Christopher A. Choquette-Choo, Natalie Dullerud, Anvith Thudi, Varun Chandrasekaran, Nicolas Papernot
2021 J jnl
Proof-of-Learning: Definitions and Practice.
CoRR
Hengrui Jia, Mohammad Yaghini, Christopher A. Choquette-Choo, Natalie Dullerud, Anvith Thudi, Varun Chandrasekaran, Nicolas Papernot
2021 J jnl
SoK: Machine Learning Governance.
CoRR
Varun Chandrasekaran, Hengrui Jia, Anvith Thudi, Adelin Travers, Mohammad Yaghini, Nicolas Papernot
2021 J jnl
Unrolling SGD: Understanding Factors Influencing Machine Unlearning.
CoRR
Anvith Thudi, Gabriel Deza, Varun Chandrasekaran, Nicolas Papernot