Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Thompson Sampling Efficiently Learns to Control Diffusion Processes
Mohamad Kazem Shirani Faradonbeh, Mohamad Sadegh Shirani Faradonbeh, Mohsen Bayati
Read the paperCheck your idea against 137,217 papers
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 |
|---|---|---|---|
| Thompson sampling policy instead of Randomized Estimate policy for exploration | Algorithm 2 (TS control) · X-29A flight control, 100 repetitions (Figure 1 right) | worst-case normalized regret | Improved |
| Thompson sampling versus Randomized Estimate on average-case regret and estimation error | Algorithm 2 (TS control) · X-29A flight control (Figure 1 right) | average normalized regret and estimation error | Improved |
| Increase stabilization duration tau from 4 to 20 seconds | Algorithm 1 (stabilization) · X-29A flight control, 1000 runs (Figure 1 left) | stabilization failure probability | Improved |
Closest papers by meaning
- No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes (NeurIPS 2025 · similarity 0.87)
- Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and Convergence (ICML 2025 · similarity 0.87)
- Diffusion Spectral Representation for Reinforcement Learning (NeurIPS 2024 · similarity 0.86)
- Safe and Stable Control via Lyapunov-Guided Diffusion Models (NeurIPS 2025 · similarity 0.86)
- Learning to Sample From Diffusion Models via Inverse Reinforcement Learning (NeurIPS 2026 · similarity 0.86)
- ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Scheduling (NeurIPS 2026 · similarity 0.86)
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.
