Research map / Bandits and online learning / Multi-armed bandits
Polynomial Cost of Adaptation for X-Armed Bandits
Hedi Hadiji
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 MeDZO to adapt to unknown Hölder regularity with input B | Continuum-armed bandits · Hölder cumulative regret, known horizon | expected cumulative regret: 412 \, (\log_2 B)^{3/2} \max \big( B , \, T L^{1/(\alpha + 1) }B^{-\alpha / (\alpha + 1)} \, \big) | Improved |
| Tune the anytime MeDZO input to m | MeDZO · Hölder cumulative regret, unknown smoothness | regret rate exponent: {\mathcal O} \big( (\log T)^{3/2}\, T^{\theta_m(\alpha)}\big) | Improved |
| Set B = \sqrt T | MeDZO · Hölder cumulative regret | expected cumulative regret: 146 \, (\log_2 T )^{3/2} \, L^{1 / (\alpha + 1)}\, T^{(\alpha +2)/(2\alpha + 2)} | Improved |
| Use GPO cross-validation among candidate discretizations | GPO with CAB1.1 · Hölder simple regret, unknown smoothness | simple regret: \big(54 + \frac{\sqrt{\pi}}{2} \log_2 T \big) L^{1 / (2\alpha +1)} \bigg(\frac{\ceil{\log_2 T}}{T}\bigg)^{\alpha / (2\al | Improved |
| Adapt to Hölder smoothness for cumulative rather than simple regret | Continuum-armed bandits · Hölder cumulative regret | regret rate: L^{1/(1+ \alpha)} T^{(\alpha + 2)/(2\alpha + 2)} | Mixed |
Closest papers by meaning
- Adaptation to the Range in K-Armed Bandits (JMLR 2023 · similarity 0.90)
- Adaptive Algorithms for Infinitely Many-Armed Bandits: A Unified Framework (JMLR 2026 · similarity 0.89)
- Generalized Linear Bandits with Limited Adaptivity (NeurIPS 2024 · similarity 0.89)
- Bayesian Regret Minimization in Offline Bandits (ICML 2024 · similarity 0.88)
- Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates (NeurIPS 2024 · similarity 0.88)
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice (ICLR 2024 · 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.
