Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Learning from eXtreme Bandit Feedback
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 POXM instead of the logging policy | AttentionXML on EUR-Lex · EUR-Lex | R@3: 33.79 -> 52.38 | Helped |
| Use POXM instead of the strongest competing bandit-feedback baseline | AttentionXML on EUR-Lex · EUR-Lex | R@3: 39.58 -> 52.38 | Helped |
| Use POXM instead of the logging policy | AttentionXML on Wiki10-31K · Wiki10-31K | R@3: 42.49 -> 60.45 | Helped |
| Use POXM instead of the strongest competing bandit-feedback baseline | AttentionXML on Wiki10-31K · Wiki10-31K | R@3: 49.92 -> 60.45 | Helped |
| Use POXM instead of the logging policy | AttentionXML on Amazon-670K · Amazon-670K | R@3: 17.89 -> 26.89 | Helped |
| Use POXM instead of the strongest competing bandit-feedback baseline | AttentionXML on Amazon-670K · Amazon-670K | R@3: 23.42 -> 26.89 | Helped |
| Add partial matching to BanditNet | BanditNet · EUR-Lex and other datasets | R@3: 15.60 -> 20.44; 49.92 -> 49.06; 16.83 -> 17.31 | Mixed |
| Add inverse label-propensity weighting to POXM (ablation) | POXM on EUR-Lex · EUR-Lex | PSR@3: +4.77% | Helped |
| Add inverse label-propensity weighting to POXM (ablation) | POXM on EUR-Lex · EUR-Lex | R@3: -5.38% | Hurt |
| Select the top 10 logging-policy actions for sIS (ablation) | POXM · EUR-Lex logging-policy variants | R@5 | Mixed |
Closest papers by meaning
- From Contextual Combinatorial Semi-Bandits to Bandit List Classification: Improved Sample Complexity with Sparse Rewards (NeurIPS 2025 · similarity 0.87)
- Gaussian Process Bandits for Top-k Recommendations (NeurIPS 2024 · similarity 0.87)
- Neural Dueling Bandits: Preference-Based Optimization with Human Feedback (ICLR 2025 · similarity 0.87)
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice (ICLR 2024 · similarity 0.87)
- Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown (NeurIPS 2025 · similarity 0.87)
- MultiScale Contextual Bandits for Long Term Objectives (NeurIPS 2025 · 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.