Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Contextual-Bandit Based Personalized Recommendation with Time-Varying User Interests
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 |
|---|---|---|---|
| Add piecewise-stationary change detection to LinUCB-Disjoint | LinUCB-Disjoint · Yahoo! dataset | CTR: 2.7% | Helped |
| Add piecewise-stationary change detection to LinUCB-Hybrid | LinUCB-Hybrid · Yahoo! dataset | CTR: 1.3% | Helped |
| Use an arm-specific disjoint payoff model instead of the uniform payoff model | Contextual bandits · Yahoo! dataset | CTR | Helped |
| Use an arm-specific hybrid payoff model instead of the uniform payoff model | Contextual bandits · Yahoo! dataset | CTR | Helped |
| Use personalized disjoint or hybrid payoffs instead of the uniform payoff model | Contextual bandits · Yahoo! dataset | CTR: 31.2% under the hybrid model and $29.5\%$ under the disjoint model | Helped |
| Add piecewise-stationary change detection to LinUCB-Disjoint | LinUCB-Disjoint · LastFM dataset | CTR: 2% | Helped |
| Add piecewise-stationary change detection to LinUCB-Hybrid | LinUCB-Hybrid · LastFM dataset | CTR: 2.4% | Helped |
| Use PSLinUCB-Disjoint instead of LinUCB-Disjoint | Synthetic disjoint payoff setting · Synthetic dataset | cumulative regret: 30% | Helped |
| Use a model that adapts to reward changes instead of a stationary model | Contextual bandits · Yahoo! dataset | CTR: 2.7% against LinUCB-Disjoint; 1.3% against LinUCB-Hybrid | Helped |
Closest papers by meaning
- Optimal Algorithms for Stochastic Contextual Preference Bandits (NeurIPS 2021 · similarity 0.90)
- Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action Spaces (ICML 2022 · similarity 0.89)
- Modeling Attrition in Recommender Systems with Departing Bandits (AAAI 2022 · similarity 0.88)
- Simple Projection-Free Algorithm for Contextual Recommendation with Logarithmic Regret and Robustness (NeurIPS 2026 · similarity 0.88)
- Neural Dueling Bandits: Preference-Based Optimization with Human Feedback (ICLR 2025 · similarity 0.87)
- Contextual Bandits for Unbounded Context Distributions (ICML 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.