Research map / Federated learning and privacy / Differential privacy
Improved Regret for Differentially Private Exploration in Linear MDP
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use adaptive policy updates triggered by sufficient changes in the data instead of a non-adaptive update schedule | Private LSVI-UCB for linear MDPs · Linear MDP, K episodes | regret bound: \widetilde{O}\pp{\sqrt{d^3 H^4 K} + \frac{d^{8/5} H^{11/5} K^{3/5}}{\epsilon^{2/5}}} -> \widetilde{O} \left ( d^{3/2} H^ | Helped |
| Use adaptive updates, yielding only O(log(K)) updates rather than polynomially many updates | Private LSVI-UCB · Linear MDP, K episodes | number of policy updates: O(\mathrm{poly}(K)) -> O(\log(K)) | Helped |
| Use adaptive updates to reduce privacy noise | Private LSVI-UCB · Linear MDP, K episodes | privacy cost in regret: K^{3/5} -> K^{1/2} | Helped |
Closest papers by meaning
- Local Differential Privacy for Regret Minimization in Reinforcement Learning (NeurIPS 2021 · similarity 0.93)
- Towards Differentially Private Reinforcement Learning with General Function Approximation (NeurIPS 2026 · similarity 0.91)
- Differentially Private Reinforcement Learning with Self-Play (NeurIPS 2024 · similarity 0.89)
- On the Sample Complexity of Differentially Private Policy Optimization (NeurIPS 2025 · similarity 0.89)
- Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits (NeurIPS 2026 · similarity 0.89)
- Connecting Thompson Sampling and UCB: Towards More Efficient Trade-offs Between Privacy and Regret (ICML 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.