7 papers
Efficient Public Verification of Private ML via Regularization
Zoë Ruha Bell, Anvith Thudi, Olive Franzese-McLaughlin +2
Training with differential privacy (DP) guarantees dataset members that they cannot be identified by users of the released model. However, those data providers, and, in general, th…
Gauss-Newton Unlearning for the LLM Era
Lev McKinney, Anvith Thudi, Juhan Bae +4
Standard large language model training can create models that produce outputs their trainer deems unacceptable in deployment. The probability of these outputs can be reduced using…
MixMin: Finding Data Mixtures via Convex Minimization
Anvith Thudi, Evianne Rovers, Yangjun Ruan +2
Modern machine learning pipelines are increasingly combining and mixing data from diverse and disparate sources, e.g., pre-training large language models. Yet, finding the optimal…
Fast Exact Unlearning for In-Context Learning Data for LLMs
Andrei I. Muresanu, Anvith Thudi, Michael R. Zhang +1
Modern machine learning models are expensive to train, and there is a growing concern about the challenge of retroactively removing specific training data. Achieving exact unlearni…
Selective Prediction via Training Dynamics
Stephan Rabanser, Anvith Thudi, Kimia Hamidieh +5
Selective Prediction is the task of rejecting inputs a model would predict incorrectly on. This involves a trade-off between input space coverage (how many data points are accepted…
Leveraging Per-Instance Privacy for Machine Unlearning
Nazanin Mohammadi Sepahvand, Anvith Thudi, Berivan Isik +5
We present a principled, per-instance approach to quantifying the difficulty of unlearning via fine-tuning. We begin by sharpening an analysis of noisy gradient descent for unlearn…