Research map / Bandits and online learning / RL theory and MDPs
Learning in Prophet Inequalities with Noisy Observations
Jung-hun Kim, Vianney Perchet
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 |
|---|---|---|---|
| use LCB-thresholding learning algorithms (ETD-LCBT, epsilon-Greedy-LCBT) instead of Gusein-Zade rule | i.i.d. prophet inequality with noisy rewards · Synthetic i.i.d. (n=100,000, d=2) | competitive ratio | Improved |
| increase observation noise sigma^2 (ablation) | ETD-LCBT vs Gusein-Zade · Synthetic i.i.d. (n=100,000, d=2) | competitive ratio gap | Improved |
| add window access to ETD-LCBT for non-identical distributions (ablation) | ETD-LCBT (non-iid) · Synthetic non-identical (n=30,000, d=2) | competitive ratio | Improved |
| use ETD-LCBT variants instead of Gusein-Zade rule | non-identical prophet inequality with noisy rewards · Synthetic non-identical (n=30,000, d=2) | competitive ratio | Improved |
Closest papers by meaning
- Improved Regret and Contextual Linear Extension for Pandora's Box and Prophet Inequality (NeurIPS 2025 · similarity 0.91)
- Intrinsic Robustness of Prophet Inequality to Strategic Reward Signaling (NeurIPS 2024 · similarity 0.89)
- Lookback Prophet Inequalities (NeurIPS 2024 · similarity 0.88)
- Improved Regret Bounds for Online Fair Division with Bandit Learning (AAAI 2025 · similarity 0.87)
- Noise-Adaptive Confidence Sets for Linear Bandits and Application to Bayesian Optimization (ICML 2024 · similarity 0.87)
- Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability (NeurIPS 2024 · 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.
