Research map / Federated learning and privacy / Differential privacy
Differentially Private Federated Bayesian Optimization with Distributed Exploration
Zhongxiang Dai, Bryan Kian Hsiang Low, Patrick Jaillet
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add distributed exploration to DP-FTS | DP-FTS · Synthetic and real-world experiments | convergence | Improved |
| add distributed exploration | FTS · Synthetic and real-world experiments | convergence | Improved |
| use federated information through Thompson sampling | standard TS · Real-world experiments | convergence | Improved |
| add local sub-region exploration at initialization (ablation) | distributed exploration · Synthetic experiments | performance | Improved |
| weight agents more heavily when assigned to a particular sub-region (ablation) | distributed exploration · Synthetic experiments | performance | Improved |
| increase the number of sub-regions P (ablation) | DP-FTS-DE · Synthetic experiments | performance | Improved |
| use an overly small clipping threshold S (ablation) | DP-FTS-DE · Synthetic experiments | performance | Hurt |
| use an excessively large clipping threshold S (ablation) | DP-FTS-DE · Synthetic experiments | performance | Hurt |
| increase the subsampling probability q (ablation) | DP-FTS-DE · Synthetic and real-world experiments | utility | Improved |
| increase Gaussian noise multiplier z (ablation) | DP-FTS-DE · Synthetic and real-world experiments | utility | Hurt |
| use a smaller privacy loss by increasing z or decreasing q (ablation) | DP-FTS-DE · Real-world experiments | utility | Hurt |
| make the influence of other agents decay faster (ablation) | FTS-DE · Synthetic experiments with heterogeneous agents | performance | Improved |
Closest papers by meaning
- Mitigating the Privacy–Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy (NeurIPS 2025 · similarity 0.90)
- Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation (ICML 2025 · similarity 0.90)
- Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off (ICML 2025 · similarity 0.89)
- Private and Federated Stochastic Convex Optimization: Efficient Strategies for Centralized Systems (ICML 2024 · similarity 0.89)
- A New Federated Learning Framework Against Gradient Inversion Attacks (AAAI 2025 · similarity 0.88)
- Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement (NeurIPS 2024 · similarity 0.88)
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.
