Research map / Probabilistic and scientific modeling / Bayesian optimization
Regret-Based $(\epsilon,\delta)$-optimal Stopping Criteria for Bayesian Optimization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes regret-based (epsilon, delta)-optimal stopping criteria for Gaussian process Bayesian optimization, aiming to stop with a provable optimality guarantee on solution quality.
Problem
Standard Bayesian optimization stops after a fixed evaluation budget, wasting cost and giving no guarantee on solution quality; existing practical stopping criteria lack theoretical grounding.
Approach
Frames stopping as an (epsilon, delta)-optimality requirement on regret of GP-based BO, deriving a stopping rule with a theoretical guarantee rather than purely empirical heuristics.
Closest papers by meaning
- Stopping Bayesian Optimization with Probabilistic Regret Bounds (NeurIPS 2024 · similarity 0.93)
- Posterior Sampling-Based Bayesian Optimization with Tighter Bayesian Regret Bounds (ICML 2024 · similarity 0.92)
- Improved Regret Bounds for Gaussian Process Upper Confidence Bound in Bayesian Optimization (NeurIPS 2025 · similarity 0.90)
- Principled Preferential Bayesian Optimization (ICML 2024 · similarity 0.89)
- Bayesian Optimisation with Unknown Hyperparameters: Regret Bounds Logarithmically Closer to Optimal (NeurIPS 2024 · similarity 0.89)
- Gaussian Process Upper Confidence Bound Achieves Nearly-Optimal Regret in Noise-Free Gaussian Process Bandits (NeurIPS 2025 · 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.