no code implementations • 17 Jan 2024 • Arun Ganesh
We give a procedure for computing group-level $(\epsilon, \delta)$-DP guarantees for DP-SGD, when using Poisson sampling or fixed batch size sampling.
no code implementations • 24 Oct 2023 • Christopher A. Choquette-Choo, Arun Ganesh, Thomas Steinke, Abhradeep Thakurta
In this paper, we propose "MMCC", the first algorithm to analyze privacy amplification via sampling for any generic matrix mechanism.
no code implementations • 10 Oct 2023 • Christopher A. Choquette-Choo, Krishnamurthy Dvijotham, Krishna Pillutla, Arun Ganesh, Thomas Steinke, Abhradeep Thakurta
We characterize the asymptotic learning utility for any choice of the correlation function, giving precise analytical bounds for linear regression and as the solution to a convex program for general convex functions.
no code implementations • 19 Feb 2023 • Arun Ganesh, Mahdi Haghifam, Milad Nasr, Sewoong Oh, Thomas Steinke, Om Thakkar, Abhradeep Thakurta, Lun Wang
To explain this phenomenon, we hypothesize that the non-convex loss landscape of a model training necessitates an optimization algorithm to go through two phases.
no code implementations • 4 Oct 2022 • Virat Shejwalkar, Arun Ganesh, Rajiv Mathews, Om Thakkar, Abhradeep Thakurta
Empirically, we show that the last few checkpoints can provide a reasonable lower bound for the variance of a converged DP model.
no code implementations • 4 Apr 2022 • Arun Ganesh, Abhradeep Thakurta, Jalaj Upadhyay
In this paper we provide an algorithmic framework based on Langevin diffusion (LD) and its corresponding discretizations that allow us to simultaneously obtain: i) An algorithm for sampling from the exponential mechanism, whose privacy analysis does not depend on convexity and which can be stopped at anytime without compromising privacy, and ii) tight uniform stability guarantees for the exponential mechanism.
no code implementations • 1 Dec 2021 • Ehsan Amid, Arun Ganesh, Rajiv Mathews, Swaroop Ramaswamy, Shuang Song, Thomas Steinke, Vinith M. Suriyakumar, Om Thakkar, Abhradeep Thakurta
In this paper, we revisit the problem of using in-distribution public data to improve the privacy/utility trade-offs for differentially private (DP) model training.
no code implementations • NeurIPS 2020 • Arun Ganesh, Kunal Talwar
Various differentially private algorithms instantiate the exponential mechanism, and require sampling from the distribution $\exp(-f)$ for a suitable function $f$.