Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Meta-Learning for Simple Regret Minimization
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 |
|---|---|---|---|
| Adapt the task prior across sequential tasks | Gaussian MAB · Gaussian MAB | average meta simple regret | Helped |
| Adapt the task prior across sequential tasks | Gaussian MAB · Gaussian MAB | average meta simple regret | Mixed |
| Use Bayesian meta-learning instead of a misspecified meta-prior (ablation) | B-metaSRM · Gaussian MAB | average meta simple regret | Helped |
| Use Bayesian meta-learning instead of agnostic TS | B-metaSRM and f-metaSRM · Linear Gaussian bandits | average meta simple regret | Helped |
| Use a Bayesian meta-prior perturbed by uniform noise from [-50, 50] (ablation) | B-metaSRM · Gaussian MAB | average meta simple regret | Hurt |
| Use a Bayesian meta-prior perturbed by uniform noise from [-50, 50] (ablation) | B-metaSRM · Linear Gaussian bandits | average meta simple regret | No clear effect |
| Transfer prior information across tasks | Meta-learning algorithms · Linear Gaussian bandits | average meta simple regret | Helped |
| Use Bayesian prior learning instead of frequentist prior estimation | B-metaSRM vs f-metaSRM · Linear Gaussian bandits | average meta simple regret | Helped |
| Increase the number of arms | Meta-learning algorithms · Gaussian MAB | average meta simple regret | Mixed |
| Increase the linear dimension | Bandit algorithms · Linear Gaussian bandits | average meta simple regret | Hurt |
Closest papers by meaning
- A Classification View on Meta Learning Bandits (ICML 2025 · similarity 0.90)
- p-Mean Regret for Stochastic Bandits (AAAI 2025 · similarity 0.90)
- Bayesian Regret Minimization in Offline Bandits (ICML 2024 · similarity 0.89)
- Test-Time Regret Minimization in Meta Reinforcement Learning (ICML 2024 · similarity 0.89)
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice (ICLR 2024 · similarity 0.89)
- Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals (ICML 2024 · 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.