Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Information-Theoretic Safe Exploration with Gaussian Processes
Alessandro Giacomo Bottero, Carlos E. Luis, Julia Vinogradska, Felix Berkenkamp, Jan Peters
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 a too small or too large Lipschitz constant L in StageOpt exploration (ablation) | StageOpt · 1D f(x)=exp(-x)+0.05 | percentage of domain classified safe | Hurt |
| Replace StageOpt (Lipschitz-based expanders) with ISE information-gain acquisition | safe exploration · 2D GP samples (100 samples, 100 iterations) | percentage of domain classified safe | Improved |
| Compare ISE with the heuristic SafeOpt-inspired acquisition | ISE · 2D GP samples | percentage of domain classified safe | No clear effect |
| Use ISE instead of StageOpt | safe exploration · 2D GP samples | percentage of safety violations per run | No clear effect |
| Use ISE instead of StageOpt | safe exploration · Cart pole controller (3D) | percentage of true safe set classified safe | No clear effect |
| Use LineBO version of ISE exploiting observation noise instead of StageOpt-like exploration | ISE · 9D and 10D heteroskedastic noise | simple regret | Improved |
Closest papers by meaning
- Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency (ICML 2024 · similarity 0.86)
- Robust and Computation-Aware Gaussian Processes (NeurIPS 2025 · similarity 0.85)
- Gaussian Process Upper Confidence Bound Achieves Nearly-Optimal Regret in Noise-Free Gaussian Process Bandits (NeurIPS 2025 · similarity 0.85)
- Bayesian Analysis of Combinatorial Gaussian Process Bandits (ICLR 2025 · similarity 0.85)
- Conditioning Gaussian Processes on Almost Anything (NeurIPS 2026 · similarity 0.84)
- Computation-Aware Gaussian Processes: Model Selection And Linear-Time Inference (NeurIPS 2024 · similarity 0.84)
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.
