Research map / Bandits and online learning / Multi-armed bandits
Crush Optimism with Pessimism: Structured Bandits Beyond Asymptotic Optimality
Kwang-Sung Jun, Chicheng Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 pessimism-guided, forced-sampling-free exploration in place of forced sampling | CROP · Finite structured bandits | expected regret: P_1 ln(n) + P_2 ln(ln(n)) + P_3 (ln(|F|) + ln(Q_1)) + K_ψ Δ_max | Improved |
| Use CROP rather than forced sampling | Cheating code, K ≈ n · Cheating code | regret: CROP: ln^3(n); forced sampling: linear regret | Improved |
| Rely on the asymptotically optimal oracle across problem instances | Clairvoyant oracle · Cheating code problem family | worst-case regret: linear regret | Hurt |
Closest papers by meaning
- An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits (NeurIPS 2020 · similarity 0.90)
- Bayesian Regret Minimization in Offline Bandits (ICML 2024 · similarity 0.90)
- Minimal Exploration in Structured Stochastic Bandits (NeurIPS 2017 · similarity 0.89)
- Block Optimism for Nonstationary Bandits with Latent Linear Dynamics (NeurIPS 2026 · similarity 0.89)
- Greedy Algorithms for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure (NeurIPS 2025 · similarity 0.89)
- Regret minimization in Linear Bandits with offline data via extended D-optimal exploration. (NeurIPS 2026 · 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.
