Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Regret Bounds for Gaussian-Process Optimization in Large Domains
Manuel Wuthrich, Bernhard Schölkopf, Andreas Krause
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 |
|---|---|---|---|
| Use EI (always maximise) instead of EI2 (alternate max/min evaluations) (ablation) | EI · continuous GP samples, 1000 grid points | evaluations to reach regret: 0.5t_ei2 <= t_ei <= t_ei2 | Improved |
| Use EI instead of EI2 (ablation) | EI · continuous D=3, l=0.030, R=1.5 | step ratio: 1.06 | Hurt |
| Use EI instead of EI2 (ablation) | EI · continuous D=4, l=0.300, R=0.5 | step ratio: 0.70 | Improved |
| Use UCB instead of UCB2 (ablation) | UCB · continuous domains with fixed confidence level | step ratio: 0.66 | Improved |
| Use UCB instead of UCB2 (ablation) | UCB · continuous D=2, l=0.030, R=2.5 | step ratio: 0.67 | Improved |
| Use EI instead of EI2 (ablation) | EI · band covariance N=100 | step ratio: 0.75 | Improved |
| Use UCB instead of UCB2 (ablation) | UCB · band covariance N=100, band_size=40 | step ratio: 1.00 | No clear effect |
| Use EI instead of EI2 (ablation) | EI · Wishart covariance N=200 | step ratio: 0.67 | Improved |
| Use UCB instead of UCB2 (ablation) | UCB · Wishart covariance N=200 | step ratio: 0.81 | Improved |
| Increase length-scale l to large values with low dimension | EI vs EI2 · continuous domains | step ratio: 1.00 | No clear effect |
| Very small length-scale (no correlation between points) | EI vs EI2 · continuous domains | step ratio: 1.00 | No clear effect |
Closest papers by meaning
- Improved Regret Bounds for Gaussian Process Upper Confidence Bound in Bayesian Optimization (NeurIPS 2025 · similarity 0.93)
- Gaussian Process Upper Confidence Bound Achieves Nearly-Optimal Regret in Noise-Free Gaussian Process Bandits (NeurIPS 2025 · similarity 0.90)
- Improved Regret Analysis For Parallel Gaussian Process Bandit Optimization (NeurIPS 2026 · similarity 0.90)
- Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary Variance (ICML 2025 · similarity 0.89)
- Posterior Sampling-Based Bayesian Optimization with Tighter Bayesian Regret Bounds (ICML 2024 · similarity 0.89)
- 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.
