Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Proportional Response: Contextual Bandits for Simple and Cumulative 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 |
|---|---|---|---|
| Increase the trade-off parameter ω | ω-RAPR · Stochastic contextual bandits | simple regret: O(1/\sqrt{\omega}) | Helped |
| Increase the trade-off parameter ω | ω-RAPR · Stochastic contextual bandits | cumulative regret: O(\sqrt{\omega}) | Hurt |
| Use ω=1 rather than a larger trade-off setting | ω-RAPR · Stochastic contextual bandits | cumulative regret: \sqrt{\omega} | Helped |
| Use ω=K | ω-RAPR · Stochastic contextual bandits with few Δ-optimal arms | simple regret: \tilde{\mathcal{O}}(\sqrt{(A+K\lambda)d/T}) | Helped |
| Use conformal arm sets with proportional-response sampling and risk adjustment | ω-RAPR · Stochastic contextual bandits | simple regret: O(1/\sqrt{\omega}) | Helped |
| Require instance-dependent simple regret while retaining minimax-optimal cumulative regret | Contextual bandit algorithms · Instances with (A,λ,Δ)=(1,0,0.24) | cumulative regret: \Tilde{\Omega}( \sqrt{K/\phi} \sqrt{KT\log F} ) | Hurt |
| Apply RAPR in the reported simulation setting | RAPR · R² context space, eight arms, linear models, horizon 5000 | runtime: less than 9 seconds | Helped |
Closest papers by meaning
- Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action Spaces (ICML 2022 · similarity 0.91)
- Context-lumpable stochastic bandits (NeurIPS 2023 · similarity 0.91)
- Optimal Regret for Policy Optimization in Contextual Bandits (ICML 2026 · similarity 0.91)
- Active Context Selection Improves Simple Regret in Contextual Bandits (NeurIPS 2026 · similarity 0.90)
- Mixed-Effects Contextual Bandits (AAAI 2024 · similarity 0.90)
- Contextual Bandits for Unbounded Context Distributions (ICML 2025 · similarity 0.90)
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.