Research map / Bandits and online learning / Contextual bandits and Thompson sampling
The Cost of Information: Phase Transitions in Contextual Bandits with Paid Observations
Xueping Gong, Jiheng Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| replace enumerated policy class (Algorithm 1) with function-approximation oracle (Algorithm 3) | paid-observation contextual bandit · Run time (T=40000, |A|=10, d=8) | execution time (s): 94.0 -> 2.0 | Improved |
| increase policy class size from 10 to 40 (ablation) | Algorithm 1 · Run time (T=40000, |A|=10, d=8) | execution time (s): 33.2 s to 94.0 s | Hurt |
| make observation-cost-aware (Algorithm 3 vs linUCB) | linUCB · d=10, |A|=5, T=10000, c=0.5 | final average cumulative regret: 5003.32 -> 2899.75 | Improved |
| Algorithm 3 versus Tucker et al. 2023 | cost-aware baseline · d=10, |A|=5, T=10000, c=0.5 | final average cumulative regret: 3697.13 -> 2899.75 | Improved |
| larger policy space (ablation) | Algorithm 1 · synthetic grid | cumulative regret | Hurt |
| more actions (ablation) | Algorithm 1 · synthetic grid | cumulative regret | Hurt |
| increase context dimension d from 2 to 8 (ablation) | Algorithm 1 · synthetic grid | cumulative regret | No clear effect |
Closest papers by meaning
- Efficient Algorithms for Adversarial Contextual Learning (ICML 2016 · similarity 0.91)
- Active Context Selection Improves Simple Regret in Contextual Bandits (NeurIPS 2026 · similarity 0.89)
- No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need! (NeurIPS 2025 · similarity 0.89)
- Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback (NeurIPS 2025 · similarity 0.89)
- Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback (NeurIPS 2024 · similarity 0.89)
- No-Regret is not enough! Bandits with General Constraints through Adaptive Regret Minimization (ICML 2025 · similarity 0.89)
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.
