Differentially Private Empirical Risk Minimization with Non-convex Loss Functions

Di Wang, Changyou Chen, Jinhui Xu

Type: Article

Publication Date: 2019-05-24

Citations: 31

Locations

International Conference on Machine Learning - View

Similar Works

Action	Title	Year	Authors
+	Differentially private convex optimization for empirical risk minimization and high-dimensional regression	2013	Abhradeep Thakurta
+	Differentially private empirical risk minimization for AUC maximization	2021	Puyu Wang Zhenhuan Yang Yunwen Lei Yiming Ying Hai Zhang
+ PDF Chat	Differentially Private Empirical Risk Minimization with Input Perturbation	2017	Kazuto Fukuchi Quang Khai Tran Jun Sakuma
+	Differentially Private Empirical Risk Minimization Revisited: Faster and More General	2018	Di Wang Minwei Ye Jinhui Xu
+	Differentially Private Empirical Risk Minimization Revisited: Faster and More General	2018	Di Wang Minwei Ye Jinhui Xu
+	Differentially Private Empirical Risk Minimization in Non-interactive Local Model via Polynomial of Inner Product Approximation.	2018	Di Wang Adam Smith Jinhui Xu
+	Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds	2014	Raef Bassily Adam Smith Abhradeep Thakurta
+	Differentially Private Non-Convex Optimization under the KL Condition with Optimal Rates	2023	Michael Menart Enayat Ullah Raman Arora Raef Bassily Cristóbal Guzmán
+	Private Non-smooth Empirical Risk Minimization and Stochastic Convex Optimization in Subquadratic Steps	2021	Janardhan Kulkarni Yin Tat Lee Daogao Liu
+	Private Empirical Risk Minimization Beyond the Worst Case: The Effect of the Constraint Set Geometry	2014	Kunal Talwar Abhradeep Thakurta Li Zhang
+	Renyi Differentially Private ERM for Smooth Objectives	2019	Chen Chen Jae Wook Lee Daniel Kifer
+ PDF Chat	High-Dimensional Private Empirical Risk Minimization by Greedy Coordinate Descent	2022	Paul Mangold Aurélien Bellet Joseph Salmon Marc Tommasi
+	Consistency of Empirical Risk Minimization for Unbounded Loss Functions	2009	Marco Muselli Francesca Ruffino
+	Efficient Privacy-Preserving Stochastic Nonconvex Optimization	2019	Lingxiao Wang Bargav Jayaraman David Evans Quanquan Gu
+	Differentially Private Objective Perturbation: Beyond Smoothness and Convexity	2019	Seth Neel Aaron Roth Giuseppe Vietri Zhiwei Steven Wu
+ PDF Chat	Empirical Risk Minimization for Losses without Variance	2025	Guanhua Fang Ping Li Gennady Samorodnitsky
+	Differentially Private Stochastic Optimization: New Results in Convex and Non-Convex Settings	2021	Raef Bassily Cristóbal Guzmán Michael Menart
+	Private Stochastic Convex Optimization with Optimal Rates	2019	Raef Bassily Vitaly Feldman Kunal Talwar Abhradeep Thakurta
+	Differentially Private Coordinate Descent for Composite Empirical Risk Minimization	2021	Paul Mangold Aurélien Bellet Joseph Salmon Marc Tommasi
+	Oracle Efficient Private Non-Convex Optimization	2019	Seth Neel Aaron Roth Giuseppe Vietri Zhiwei Steven Wu

Works That Cite This (21)

Action	Title	Year	Authors
+	Differentially Private Bayesian Inference for Generalized Linear Models	2020	Tejas Kulkarni Joonas Jälkö Antti Koskela Samuel Kaski Antti Honkela
+	Evading Curse of Dimensionality in Unconstrained Private GLMs via Private Gradient Descent	2020	Shuang Song Thomas Steinke Om Thakkar Abhradeep Thakurta
+ PDF Chat	Large Scale Private Learning via Low-rank Reparametrization	2021	Dahua Yu Huishuai Zhang Wei Chen Jian Yin Tie‐Yan Liu
+	Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Non-Convex Stochastic Optimization: Non-Asymptotic Performance Bounds and Momentum-Based Acceleration	2018	Xuefeng Gao Mert Gürbüzbalaban Lingjiong Zhu
+	On Differentially Private Stochastic Convex Optimization with Heavy-tailed Data	2020	Di Wang Hanshen Xiao Srini Devadas Jinhui Xu
+ PDF Chat	Privacy-Aware Rejection Sampling	2021	Jordan Awan Vinayak Rao
+ PDF Chat	Differentially Private Learning with Per-Sample Adaptive Clipping	2023	Tianyu Xia Shuheng Shen Su Yao Xinyi Fu Ke Xu Xiaolong Xu Xing Fu
+	On Dynamic Noise Influence in Differential Private Learning	2021	Junyuan Hong Zhangyang Wang Jiayu Zhou
+	Faster Rates of Differentially Private Stochastic Convex Optimization.	2021	Jinyan Su Di Wang
+	Differentially Private Bayesian Neural Networks on Accuracy, Privacy and Reliability	2021	Qiyiwen Zhang Zhiqi Bu Kan Chen Qi Long

Works Cited by This (27)

Action	Title	Year	Authors
+	Diffusion for Global Optimization in $\mathbb{R}^n $	1987	Tzuu-Shuh Chiang Chii-Ruey Hwang Shuenn Jyi Sheu
+	Differentially Private Empirical Risk Minimization.	2011	Kamalika Chaudhuri Claire Monteleoni Anand D. Sarwate
+	Private Convex Empirical Risk Minimization and High-dimensional Regression	2012	Daniel Kifer Adam Smith Abhradeep Thakurta
+	On the Convergence of Stochastic Gradient MCMC Algorithms with High-Order Integrators	2016	Changyou Chen Nan Ding Lawrence Carin
+	Exploration of the (non-)asymptotic bias and variance of stochastic gradient langevin dynamics	2016	Sebastian J. Vollmer Konstantinos C. Zygalakis Yee Whye Teh
+	Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis	2017	Maxim Raginsky Alexander Rakhlin Matus Telgarsky
+	No spurious local minima in nonconvex low rank problems: a unified geometric analysis	2017	Rong Ge Chi Jin Yi Zheng
+	Regularized M-estimators with nonconvexity: statistical and algorithmic theory for local optima	2015	Po‐Ling Loh Martin J. Wainwright
+	Escaping Saddle Points in Constrained Optimization	2018	Aryan Mokhtari Asuman Ozdaglar Ali Jadbabaie
+ PDF Chat	The landscape of empirical risk for nonconvex losses	2018	Mei Song Yu Bai Andrea Montanari