Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Bandits with Knapsacks beyond the Worst Case
Karthik Abinav Sankararaman, Aleksandrs Slivkins
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 |
|---|---|---|---|
| Analyze PrunedUcbBwK under d=2 and best-arm-optimality | UcbBwK · BwK | regret vs. best fixed distribution: \mO(KG_\term{LAG}^{-2}\,\log T) | Improved |
| Use the tighter counting argument when the best arm's consumption is sufficiently far from B/T | PrunedUcbBwK · BwK, d=2 and best-arm-optimal | regret vs. best fixed distribution: \mO (\; \sum_{a\not\in\{a^*,\term{null}\}} G_\term{LAG}^{-1}(a)\; \log(Kd T)\;) | Improved |
| Apply the confidence-sum reduction to MnlBwK | BwK-to-bandits reduction · MnlBwK | worst-case regret dependence on N: N^{7/2} -> N^{3/2} | Improved |
Closest papers by meaning
- No-Regret is not enough! Bandits with General Constraints through Adaptive Regret Minimization (ICML 2025 · similarity 0.93)
- High-dimensional Linear Bandits with Knapsacks (ICML 2024 · similarity 0.91)
- Bandits with Replenishable Knapsacks: the Best of both Worlds (ICLR 2024 · similarity 0.91)
- Contextual Decision-Making with Knapsacks Beyond the Worst Case (NeurIPS 2024 · similarity 0.90)
- Piecewise-Stationary Bandits with Knapsacks (NeurIPS 2024 · similarity 0.89)
- On the Minimax Regret for Contextual Linear Bandits and Multi-Armed Bandits with Expert Advice (NeurIPS 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.
