Private Learning Implies Online Learning: An Efficient Reduction
Not on the map. Why?
Abstract (arXiv)
We study the relationship between the notions of differentially private learning and online learning in games. Several recent works have shown that differentially private learning implies online learning, but an open problem of Neel, Roth, and Wu citeNeelAaronRoth2018 asks whether this implication is it efficient. Specifically, does an efficient differentially private learner imply an efficient online learner? In this paper we resolve this open question in the context of pure differential privacy. We derive an efficient black-box reduction from differentially private learning to online learning from expert advice.
Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). First posted on arXiv 27 May 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 3; 2022: 0; 2023: 1; 2024: 3; 2025: 2; 2026: 1.
10 papers.
- 2021A Theory of PAC Learnability of Partial Concept Classescited by 60
- 2023Near Optimal Memory-Regret Tradeoff for Online Learningcited by 15
- 2021Private learning implies quantum stabilitycited by 10
- 2024On the Computational Landscape of Replicable Learningcited by 7
- 2024Private PAC Learning May be Harder than Online Learningcited by 4
- 2021Optimal Query Complexity of Secure Stochastic Convex Optimizationcited by 1
- 2024Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-upscited by 1
- 2025Private Online Learning against an Adaptive Adversary: Realizable and Agnostic Settingscited by 1
- 2025On the Inherent Privacy of Zeroth Order Projected Gradient Descentcited by 0
- 2026From Average Sensitivity to Small-Loss Regret Bounds under Random-Order Modelcited by 0
- 2026From Average Sensitivity to Small-Loss Regret Bounds under Random-Order Model10 Feb 2026
- 2025Private Online Learning against an Adaptive Adversary: Realizable and Agnostic Settings1 Oct 2025
- 2025On the Inherent Privacy of Zeroth Order Projected Gradient Descent8 Jul 2025
- 2024Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups27 Sep 2024
- 2024On the Computational Landscape of Replicable Learning24 May 2024
- 2024Private PAC Learning May be Harder than Online Learning16 Feb 2024
- 2023Near Optimal Memory-Regret Tradeoff for Online Learning3 Mar 2023
- 2021A Theory of PAC Learnability of Partial Concept Classes18 Jul 2021
- 2021Optimal Query Complexity of Secure Stochastic Convex Optimization5 Apr 2021
- 2021Private learning implies quantum stability14 Feb 2021