Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks

31 October 2023

Papers citing "Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks"

7 / 7 papers shown

Title
Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions Sitan Chen Sinho Chewi Jungshian Li Yuanzhi Li Adil Salim Anru R. Zhang DiffM 123 245 0 22 Sep 2022
Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization) Zhenyu Zhu Fanghui Liu Grigorios G. Chrysos V. Cevher 35 19 0 15 Sep 2022
Parameters or Privacy: A Provable Tradeoff Between Overparameterization and Membership Inference Jasper Tan Blake Mason Hamid Javadi Richard G. Baraniuk FedML 29 19 0 02 Feb 2022
When is the Convergence Time of Langevin Algorithms Dimension Independent? A Composite Optimization Viewpoint Y. Freund Yi-An Ma Tong Zhang 18 16 0 05 Oct 2021
Differentially Private Stochastic Optimization: New Results in Convex and Non-Convex Settings Raef Bassily Cristóbal Guzmán Michael Menart 39 54 0 12 Jul 2021
Extracting Training Data from Large Language Models Nicholas Carlini Florian Tramèr Eric Wallace Matthew Jagielski Ariel Herbert-Voss ... Tom B. Brown D. Song Ulfar Erlingsson Alina Oprea Colin Raffel MLAU SILM 267 1,808 0 14 Dec 2020
Stochastic Gradient Descent for Non-smooth Optimization: Convergence Results and Optimal Averaging Schemes Ohad Shamir Tong Zhang 99 570 0 08 Dec 2012