Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Learning from Ranking Feedback: Improved Regret Bounds via Independence Preserving Rank Breaking
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Studies online assortment selection with ranking feedback and proposes an independence-preserving rank breaking approach to obtain improved regret bounds.
Problem
Sequential decision-making where the learner selects a bounded-size assortment each round and observes a ranking of the selected items rather than absolute scores, which are poorly calibrated across evaluators.
Approach
Uses rank breaking to convert each observed ranking into pairwise comparisons while preserving statistical independence among the resulting observations, yielding improved regret bounds for ranking-feedback bandits.
Key results
- Proposes independence-preserving rank breaking for learning from ranking feedback in sequential assortment selection, with improved regret bounds claimed over prior analyses (exact bounds not stated in the abstract).
Limitations
- Full text unavailable; experimental validation and exact bound details not verifiable from the abstract.
Experimental setup
Metrics: regret
Builds on: rank breaking
Closest papers by meaning
- Bandits with Ranking Feedback (NeurIPS 2024 · similarity 0.91)
- Adaptively Learning to Select-Rank in Online Platforms (ICML 2024 · similarity 0.88)
- Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds (ICML 2025 · similarity 0.88)
- Eliciting Kemeny Rankings (AAAI 2024 · similarity 0.87)
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice (ICLR 2024 · similarity 0.87)
- Neural Dueling Bandits: Preference-Based Optimization with Human Feedback (ICLR 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.