Research map / Bandits and online learning / Online convex optimization and games
Pricing a Low-regret Seller
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 Algorithm 1 instead of EXP3.P baseline | Pricing buyer · Simulation, T=10^6 | regret: 587196 -> 74817 | Helped |
| Use Algorithm 2 instead of EXP3.P baseline | Pricing buyer · Simulation, T=10^6 | regret: 587196 -> 15236 | Helped |
| Use Algorithm 2 instead of Algorithm 1 | Pricing buyer · Simulation, T=10^6 | regret: 74817 -> 15236 | Helped |
| Use Algorithm 1 instead of baseline | Pricing buyer · Simulation, T=10^6 | rounds not selected: 840149 -> 61110 | Helped |
| Use Algorithm 2 instead of Algorithm 1 | Pricing buyer · Simulation, T=10^6 | rounds not selected: 61110 -> 8585 | Helped |
| Use Algorithm 2 instead of Algorithm 1 | Pricing buyer · Simulation, T=10^6 | extra payment: 32040 -> 9227 | Helped |
| Baseline pays no extra to seller but is rarely selected | EXP3.P baseline · Simulation, T=10^6 | extra payment: -908 | Mixed |
| Grid search Algorithm 1 parameters a, beta, theta (ablation) | Algorithm 1 · Simulation, T=10^6 | regret: a = 2, beta = 1.5, theta = 0.2 | Helped |
| Grid search Algorithm 2 alpha and beta (ablation) | Algorithm 2 · Simulation, T=10^6 | regret: alpha = 0.1, beta = 0.5 | Helped |
| Vary outside-option price distribution parameters (ablation) | Algorithms 1 and 2 · Simulation, T=10^6 | regret | No clear effect |
| Time scaling of regret | Algorithms 1, 2 vs baseline · Simulation, T=10^6 | regret growth | Helped |
Closest papers by meaning
- Learning to Clear the Market (ICML 2019 · similarity 0.85)
- Improved Online Learning Algorithms for CTR Prediction in Ad Auctions (ICML 2023 · similarity 0.84)
- Dynamic Pricing and Learning with Bayesian Persuasion (NeurIPS 2023 · similarity 0.83)
- Comparing Uniform Price and Discriminatory Multi-Unit Auctions through Regret Minimization (NeurIPS 2025 · similarity 0.82)
- Improved Algorithms for Contextual Dynamic Pricing (NeurIPS 2024 · similarity 0.81)
- Near-Optimal Regret-Queue Length Tradeoff in Online Learning for Two-Sided Markets (NeurIPS 2025 · similarity 0.81)
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.