Research map / Bandits and online learning / Online convex optimization and games
Simultaneously Learning Stochastic and Adversarial Bandits under the Position-Based Model
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 |
|---|---|---|---|
| Use FTRL-PBM with a PBM-specific self-bounding constraint and 1/2-Tsallis entropy | Online learning to rank under PBM · Stochastic environment | regret upper bound: O(\frac{mn}{\Delta_\beta \Delta} \log(T)) | Helped |
| Use FTRL-PBM with a 1/2-Tsallis entropy regularizer | Online learning to rank under PBM · Adversarial environment | regret upper bound: O(m\sqrt{nT}) | Helped |
| Replace the commonly defined suboptimality gap with a PBM-specific gap that accounts for misplaced items | FTRL-PBM stochastic regret analysis · PBM stochastic environment | regret analysis | Helped |
| Use a PBM-specific stochastic-and-adversarial algorithm rather than methods designed for only one environment | FTRL-PBM · Synthetic stochastic environments | averaged rewards | Mixed |
Closest papers by meaning
- Adversarial Attacks on Online Learning to Rank with Click Feedback (NeurIPS 2023 · similarity 0.89)
- Bandits with Ranking Feedback (NeurIPS 2024 · similarity 0.87)
- Online Learning in the Random-Order Model (ICML 2025 · similarity 0.87)
- Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints (NeurIPS 2024 · similarity 0.87)
- Stochastic Bandits Robust to Adversarial Attacks (ICLR 2025 · similarity 0.87)
- Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback (NeurIPS 2025 · similarity 0.86)
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.