13 citations · 44 across the 15 of their papers we have counts for
17 papers
Differentially Private Mixing of Public Datasets Improves Private Learning
Yufei Chen, Tejumade Afonja, Anvith Thudi +1
Many machine learning applications involve sensitive data and therefore require training under differential privacy (DP). However, DP training often degrades model utility. In some…
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…
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…
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…
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…
MixMax: Distributional Robustness in Function Space via Optimal Data Mixtures
Anvith Thudi, Chris J. Maddison
Machine learning models are often required to perform well across several pre-defined settings, such as a set of user groups. Worst-case performance is a common metric to capture t…
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…
Better Sparsifiers for Directed Eulerian Graphs
Sushant Sachdeva, Anvith Thudi, Yibin Zhao
Spectral sparsification for directed Eulerian graphs is a key component in the design of fast algorithms for solving directed Laplacian linear systems. Directed Laplacian linear sy…
Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD
Anvith Thudi, Hengrui Jia, Casey Meehan +2
Differentially private stochastic gradient descent (DP-SGD) is the canonical approach to private deep learning. While the current privacy analysis of DP-SGD is known to be tight in…
Training Private Models That Know What They Don't Know
Stephan Rabanser, Anvith Thudi, Abhradeep Thakurta +2
Training reliable deep learning models which avoid making overconfident but incorrect predictions is a longstanding challenge. This challenge is further exacerbated when learning h…
Proof-of-Learning is Currently More Broken Than You Think
Congyu Fang, Hengrui Jia, Anvith Thudi +5
Proof-of-Learning (PoL) proposes that a model owner logs training checkpoints to establish a proof of having expended the computation necessary for training. The authors of PoL for…
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…
Bounding Membership Inference
Anvith Thudi, Ilia Shumailov, Franziska Boenisch +1
Differential Privacy (DP) is the de facto standard for reasoning about the privacy guarantees of a training algorithm. Despite the empirical observation that DP reduces the vulnera…
On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning
Anvith Thudi, Hengrui Jia, Ilia Shumailov +1
Machine unlearning, i.e. having a model forget about some of its training data, has become increasingly more important as privacy legislation promotes variants of the right-to-be-f…
SoK: Machine Learning Governance
Varun Chandrasekaran, Hengrui Jia, Anvith Thudi +3
The application of machine learning (ML) in computer systems introduces not only many benefits but also risks to society. In this paper, we develop the concept of ML governance to…
Unrolling SGD: Understanding Factors Influencing Machine Unlearning
Anvith Thudi, Gabriel Deza, Varun Chandrasekaran +1
Machine unlearning is the process through which a deployed machine learning model is made to forget about some of its training data points. While naively retraining the model from…
Proof-of-Learning: Definitions and Practice
Hengrui Jia, Mohammad Yaghini, Christopher A. Choquette-Choo +4
Training machine learning (ML) models typically involves expensive iterative optimization. Once the model's final parameters are released, there is currently no mechanism for the e…