Efficient Private SCO for Heavy-Tailed Data via Clipping

v1v2v3 (latest)

Efficient Private SCO for Heavy-Tailed Data via Clipping

27 June 2022

Bo Han

ArXiv (abs)PDF HTML

Papers citing "Efficient Private SCO for Heavy-Tailed Data via Clipping"

12 / 12 papers shown

Title
High Dimensional Differentially Private Stochastic Optimization with Heavy-tailed Data Lijie Hu Shuo Ni Hanshen Xiao Di Wang 130 53 0 23 Jul 2021
Non-Euclidean Differentially Private Stochastic Convex Optimization: Optimal Rates in Linear Time Raef Bassily Cristóbal Guzmán Anupama Nandi 117 68 0 01 Mar 2021
On Differentially Private Stochastic Convex Optimization with Heavy-tailed Data Di Wang Hanshen Xiao S. Devadas Jinhui Xu 71 57 0 21 Oct 2020
Tempered Sigmoid Activations for Deep Learning with Differential Privacy Nicolas Papernot Abhradeep Thakurta Shuang Song Steve Chien Ulfar Erlingsson AAML 207 179 0 28 Jul 2020
Private Stochastic Convex Optimization: Optimal Rates in Linear Time Vitaly Feldman Tomer Koren Kunal Talwar 73 211 0 10 May 2020
Private Mean Estimation of Heavy-Tailed Distributions Gautam Kamath Vikrant Singhal Jonathan R. Ullman 87 99 0 21 Feb 2020
Private Stochastic Convex Optimization with Optimal Rates Raef Bassily Vitaly Feldman Kunal Talwar Abhradeep Thakurta 87 246 0 27 Aug 2019
Mean estimation and regression under heavy-tailed distributions--a survey Gabor Lugosi S. Mendelson 103 246 0 10 Jun 2019
Average-Case Averages: Private Algorithms for Smooth Sensitivity and Mean Estimation Mark Bun Thomas Steinke 75 76 0 06 Jun 2019
A Short Note on Concentration Inequalities for Random Vectors with SubGaussian Norm Chi Jin Praneeth Netrapalli Rong Ge Sham Kakade Michael I. Jordan 115 150 0 11 Feb 2019
Robust descent using smoothed multiplicative noise Matthew J. Holland OOD 59 27 0 15 Oct 2018
Collecting Telemetry Data Privately Bolin Ding Janardhan Kulkarni Sergey Yekhanin 68 689 0 05 Dec 2017

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.