Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior
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 |
|---|---|---|---|
| Estimate the GP prior from offline functions and use the estimated prior for BO | PEM-BO · Continuous synthetic function | best function value after 10 evaluations | No clear effect |
| Estimate the GP prior from offline functions rather than use a fixed squared exponential kernel | PEM-BO · Grasp optimization | best function value | Helped |
| Estimate the GP prior from offline functions rather than use fixed kernels on the original parameter spaces | PEM-BO · Grasp, base pose, and placement optimization | best function value | Helped |
| Use fixed squared exponential kernel assumptions instead of estimating the prior from offline data | Plain and TLSM-BO · Grasp, base pose, and placement optimization | best function value | Hurt |
| Limit the training data available to TLSM-BO | TLSM-BO · Continuous synthetic function | best function value | Hurt |
Closest papers by meaning
- Posterior Sampling-Based Bayesian Optimization with Tighter Bayesian Regret Bounds (ICML 2024 · similarity 0.90)
- Improved Regret Bounds for Gaussian Process Upper Confidence Bound in Bayesian Optimization (NeurIPS 2025 · similarity 0.90)
- Scalable Bayesian Optimization via Focalized Sparse Gaussian Processes (NeurIPS 2024 · similarity 0.89)
- Stopping Bayesian Optimization with Probabilistic Regret Bounds (NeurIPS 2024 · similarity 0.89)
- Principled Preferential Bayesian Optimization (ICML 2024 · similarity 0.88)
- Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency (ICML 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.