Data to 14 Oct 2026

Differentially Private Empirical Risk Minimization Revisited: Faster and More General

arXiv 1802.05251 ↗First posted 14 Feb 2018cs.LG cs.CR stat.MLcited by 128

Not on the map. Why?

Abstract (arXiv)

In this paper we study the differentially private Empirical Risk Minimization (ERM) problem in different settings. For smooth (strongly) convex loss function with or without (non)-smooth regularization, we give algorithms that achieve either optimal or near optimal utility bounds with less gradient complexity compared with previous work. For ERM with smooth convex loss function in high-dimensional (pgg n) setting, we give an algorithm which achieves the upper bound with less gradient complexity than previous ones. At last, we generalize the expected excess empirical risk from convex loss functions to non-convex ones satisfying the Polyak-Lojasiewicz condition and give a tighter upper bound on the utility than the one in citeijcai2017-548.

Key facts. Cited by 128 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 25; 2022: 34; 2023: 23; 2024: 20; 2025: 21; 2026: 5.

128 papers.

Sort:

By area:

2021Deep Learning with Label Differential Privacycited by 117
2021Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learningcited by 86
2023Differentially Private Diffusion Models Generate Useful Synthetic Imagescited by 86
2023Revisiting Gradient Clipping: Stochastic bias and tight convergence guaranteescited by 83
2021Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descentcited by 73
2022TAN Without a Burn: Scaling Laws of DP-SGDcited by 52
2021Non-Euclidean Differentially Private Stochastic Convex Optimization: Optimal Rates in Linear Timecited by 51
2021Public Data-Assisted Mirror Descent for Private Model Trainingcited by 49
2022When Does Differentially Private Learning Not Suffer in High Dimensions?cited by 48
2021Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Datacited by 47
2021Differentially Private Stochastic Optimization: New Results in Convex and Non-Convex Settingscited by 45
2021Survey: Leakage and Privacy at Inference Timecited by 44

38 more

2022No Free Lunch Theorem for Security and Utility in Federated Learningcited by 39
2022Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimizationcited by 36
2022SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compressioncited by 34
2022Faster Rates of Convergence to Stationary Points in Differentially Private Optimizationcited by 32
2021Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Lossescited by 30
2021Differentially private inference via noisy optimizationcited by 27
2022Muffliato: Peer-to-Peer Privacy Amplification for Decentralized Optimization and Averagingcited by 27
2022Private Non-Convex Federated Learning Without a Trusted Servercited by 26
2022Theoretical Error Performance Analysis for Variational Quantum Circuit Based Functional Regressioncited by 26
2023DPZero: Private Fine-Tuning of Language Models without Backpropagationcited by 26
2021Differentially Private SGD with Non-Smooth Lossescited by 22
2022Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimizationcited by 22
2021Private Non-smooth Empirical Risk Minimization and Stochastic Convex Optimization in Subquadratic Stepscited by 21
2022Differentially Private Learning with Per-Sample Adaptive Clippingcited by 21
2023Private estimation algorithms for stochastic block models and mixture modelscited by 21
2022Beyond Uniform Lipschitz Condition in Differentially Private Optimizationcited by 19
2023Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacycited by 18
2023Practical Differentially Private and Byzantine-resilient Federated Learningcited by 18
2021Wide Network Learning with Differential Privacycited by 17
2022Stochastic Differentially Private and Fair Learningcited by 16
2025Towards User-level Private Reinforcement Learning with Human Feedbackcited by 14
2022DPIS: An Enhanced Mechanism for Differentially Private SGD with Importance Samplingcited by 13
2024FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneitycited by 13
2021Faster Rates of Private Stochastic Convex Optimizationcited by 12
2022Differentially private Riemannian optimizationcited by 12
2023Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Riskscited by 12
2023Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learnerscited by 12
2021A Fairness Analysis on Private Aggregation of Teacher Ensemblescited by 11
2024Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergencecited by 11
2021Differentially Private Coordinate Descent for Composite Empirical Risk Minimizationcited by 10
2022Differentially Private Regression with Unbounded Covariatescited by 10
2022Momentum Aggregation for Private Non-convex ERMcited by 10
2023DIFF2: Differential Private Optimization via Gradient Differences for Nonconvex Distributed Learningcited by 10
2023Algorithmic Aspects of the Log-Laplace Transform and a Non-Euclidean Proximal Samplercited by 10
2023Differentially Private Non-convex Learning for Multi-layer Neural Networkscited by 10
2024How to Make the Gradients Small Privately: Improved Rates for Differentially Private Non-Convex Optimizationcited by 10
2023Convergence and Privacy of Decentralized Nonconvex Optimization with Gradient Clipping and Communication Compressioncited by 9
2021DP-UTIL: Comprehensive Utility Analysis of Differential Privacy in Machine Learningcited by 8

50 most cited of 128 All 128 (JSON)