Research map / Probabilistic and scientific modeling / Bayesian optimization
Distributionally-Aware Kernelized Bandit Problems for Risk Aversion
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 |
|---|---|---|---|
| Use PKE model with UCB for CVaR (CVPKE-UCB) instead of IGP-UCB mean-based baseline | kernelized CVaR bandit · Synthetic normal and log-normal environments, alpha in {0.05,0.1,0.5,0.9,0.95} | cumulative CVaR regret | Helped |
| Use CVPKE-UCB instead of IGP-UCB when CVaR level alpha is close to 1 (near expectation) on normal environments | kernelized CVaR bandit · Synthetic normal environments, alpha=0.95 | cumulative CVaR regret | Hurt |
| Use CVPKE-UCB instead of IGP-UCB in some settings where baseline incurs linear regret | kernelized CVaR bandit · Synthetic normal and log-normal environments | sublinear vs linear cumulative regret | Helped |
| Phased elimination algorithm CVPKE-PH with finitely many arms (vs CVPKE-UCB) | kernelized CVaR bandit with Matern kernels · Theory (regret bound) | regret order | Helped |
Closest papers by meaning
- On Kernelized Multi-Armed Bandits with Constraints (NeurIPS 2022 · similarity 0.91)
- On Kernelized Multi-armed Bandits (ICML 2017 · similarity 0.89)
- Sharper Guarantees for Misspecified Kernelized Bandit Optimization (NeurIPS 2026 · similarity 0.88)
- Near-Optimal Regret in Adversarial Kernel Bandits (NeurIPS 2026 · similarity 0.88)
- Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints (NeurIPS 2024 · similarity 0.88)
- Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary Variance (ICML 2025 · similarity 0.87)
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.