Research map / Bandits and online learning / Multi-armed bandits
On Kernelized Multi-armed Bandits
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 IGP-UCB instead of GP-UCB | GP bandit optimization · Synthetic RKHS functions, Squared Exponential and Matérn kernels | cumulative regret | Helped |
| Use IGP-UCB instead of GP-UCB | GP bandit optimization · Temperature sensor data | cumulative regret | No clear effect |
| Use GP-TS instead of the other compared algorithms | GP bandit optimization · Temperature sensor data | cumulative regret | Helped |
| Use GP-TS instead of the other compared algorithms | GP bandit optimization · Light sensor data | cumulative regret | Helped |
| Use GP-EI or GP-PI instead of IGP-UCB or GP-TS | GP bandit optimization · Rosenbrock and Hartman3 | cumulative regret | Helped |
| Use IGP-UCB or GP-TS on standard test functions | GP bandit optimization · Rosenbrock and Hartman3 | cumulative regret | Mixed |
| Use IGP-UCB instead of GP-EI/PI | GP bandit optimization · Light sensor data | cumulative regret | Helped |
| Use the narrower confidence width in IGP-UCB | GP-UCB · RKHS bandits | regret bound: O(\ln^{3/2}T) | Helped |
Closest papers by meaning
- Gaussian Process Upper Confidence Bound Achieves Nearly-Optimal Regret in Noise-Free Gaussian Process Bandits (NeurIPS 2025 · similarity 0.93)
- Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary Variance (ICML 2025 · similarity 0.93)
- Improved Regret Analysis For Parallel Gaussian Process Bandit Optimization (NeurIPS 2026 · similarity 0.91)
- Improved Regret Bounds for Gaussian Process Upper Confidence Bound in Bayesian Optimization (NeurIPS 2025 · similarity 0.90)
- Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency (ICML 2024 · similarity 0.90)
- Bayesian Analysis of Combinatorial Gaussian Process Bandits (ICLR 2025 · similarity 0.89)
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.