Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Parametric Graph for Unimodal Ranking Bandit
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 |
|---|---|---|---|
| learn the graph online (GRAB) instead of a static graph of degree LK (S-GRAB) (ablation) | unimodal ranking bandit · Yandex and simulated data | cumulative regret | Helped |
| use a learned graph of permutation neighborhoods (GRAB) instead of KL-CombUCB without graph (ablation) | unimodal ranking bandit · Yandex and simulated data | cumulative regret | Helped |
| GRAB vs PB-MHB on Yandex: PB-MHB is the only method with lower regret but is ~10x slower and lacks guarantees | GRAB · Yandex dataset | cumulative regret at T=10^7 | Mixed |
| use the GRAB algorithm with graph of degree L-1 instead of KL-CombUCB-style exploration | PBM ranking bandit · simulated data | computation time per trial | Helped |
Closest papers by meaning
- Efficient Contextual Bandits with Uninformed Feedback Graphs (ICML 2024 · similarity 0.87)
- Stochastic contextual bandits with graph feedback: from independence number to MAS number (NeurIPS 2024 · similarity 0.86)
- Bandits with Ranking Feedback (NeurIPS 2024 · similarity 0.86)
- PageRank Bandits for Link Prediction (NeurIPS 2024 · similarity 0.86)
- Leveraging Offline Data in Linear Latent Contextual Bandits (ICML 2025 · similarity 0.85)
- Efficient Graph Bandit Learning with Side-Observations and Switching Constraints (AAAI 2025 · similarity 0.85)
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.