Research map / Bandits and online learning / Multi-armed bandits
Blocked Collaborative Bandits: Online Collaborative Filtering with Per-Item Budget Constraints
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 phased PB-LATTICE with matrix-completion clustering instead of greedy with a fixed exploration period (m=10 or m=30) | PB-LATTICE · Synthetic D1, D2, D3 (M=150, N=150, T=60) | cumulative and round-wise reward | Helped |
| use PB-LATTICE instead of Collaborative-Greedy, which explores in every round | PB-LATTICE · Synthetic D3 (like/dislike feedback) | round-wise reward | Helped |
| shorten the greedy algorithm's exploration period (ablation) | Greedy baseline · Synthetic D1, D2 | estimation quality | Hurt |
| allow a blocking budget B = Theta(log T) instead of B = 1 prior guarantees | B-LATTICE · Worst-case regret | regret bound: T^{2/3} -> sqrt(T) | Helped |
Closest papers by meaning
- Online Clustering of Dueling Bandits (ICML 2025 · similarity 0.88)
- Leveraging Offline Data in Linear Latent Contextual Bandits (ICML 2025 · similarity 0.87)
- Online Matrix Completion: A Collaborative Approach with Hott Items (ICML 2024 · similarity 0.87)
- On Interpolating Experts and Multi-Armed Bandits (ICML 2024 · similarity 0.87)
- Regret minimization in Linear Bandits with offline data via extended D-optimal exploration. (NeurIPS 2026 · similarity 0.86)
- On Weak Regret Analysis for Dueling Bandits (NeurIPS 2024 · 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.