Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Stochastic Contextual Bandits with Long Horizon Rewards
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 sparse dependence-pattern estimation rather than rank-1 factorization as the main estimation strategy | AD-Lasso versus SA-GD · Synthetic long-horizon contextual bandits with highly sparse weights | regret | Helped |
| Use sparse dependence-pattern estimation rather than rank-1 factorization as the main estimation strategy | AD-Lasso versus SA-GD · Synthetic long-horizon contextual bandits, including cases where sd > d+h | regret | Helped |
| Estimate the dependence pattern using all nonzero weights rather than only locating the largest weight | AD-Lasso versus SW-MP and UCB-MP · Synthetic instances with spread-out weights | regret | Helped |
| Estimate the dependence pattern using all nonzero weights rather than only locating the largest weight | AD-Lasso versus SW-MP and UCB-MP · Synthetic instances with weights concentrated over few entries | regret | No clear effect |
| Place the nonzero weight mass earlier in the dependence vector | Doubling Lasso · Data-poor synthetic instances with early- and late-concentrated weights | regret | Helped |
| Rely on rank-1 structure instead of exploiting sparse dependence | Long-horizon contextual bandit estimation · Synthetic long-horizon contextual bandits | estimation quality | Hurt |
Closest papers by meaning
- Stochastic Bandits with Context Distributions (NeurIPS 2019 · similarity 0.91)
- An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits (NeurIPS 2020 · similarity 0.91)
- Active Context Selection Improves Simple Regret in Contextual Bandits (NeurIPS 2026 · similarity 0.90)
- Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits (ICML 2024 · similarity 0.90)
- Mixed-Effects Contextual Bandits (AAAI 2024 · similarity 0.90)
- High Probability Bound for Cross-Learning Contextual Bandits with Unknown Context Distributions (ICML 2025 · similarity 0.90)
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.