Research map / Bandits and online learning / Online convex optimization and games
Dynamic Incentive-Aware Learning: Robust Pricing in Contextual Auctions
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 |
|---|---|---|---|
| Estimate preferences from auction outcomes rather than the buyer's submitted bids | CORP · Contextual second-price auctions, known noise distribution | T-period regret: O\left(Nd \left(\log(Td)\log(T) +\frac{\log^2(T)}{\log^2(1/\gamma)}\right)\right) | Helped |
| Delay the use of auction outcomes until the next episode | CORP · Contextual second-price auctions, known noise distribution | T-period regret: O\left(Nd \left(\log(Td)\log(T) +\frac{\log^2(T)}{\log^2(1/\gamma)}\right)\right) | Helped |
| Add randomized exploration periods to incentivize truthful bidding | CORP · Contextual second-price auctions, known noise distribution | T-period regret: O\left(Nd \left(\log(Td)\log(T) +\frac{\log^2(T)}{\log^2(1/\gamma)}\right)\right) | Helped |
| Estimate the noise scale along with buyer preferences using MLE and pure exploration | CORP-II · Contextual second-price auctions, unknown fixed location-scale noise | T-period regret: O\left(Nd \log(Td) \sqrt{T} + N^2 d \Big(1+\frac{1}{\log^2(1/\gamma)}\Big) \log^3(T) \right) | Helped |
| Use least squares on randomized auction outcomes and robust reserves instead of estimating the changing noise distribution | SCORP · Contextual second-price auctions, unknown time-varying noise in an ambiguity set | T-period regret: O\left( N\sqrt{d \log(Td)}\; T^{2/3} +\frac{N}{\log(1/\gamma)} \log(T)\; T^{1/3} \right) | Helped |
| Increase exploration to handle time-varying noise | SCORP · Contextual second-price auctions, unknown time-varying noise in an ambiguity set | T-period regret: O\left( N\sqrt{d \log(Td)}\; T^{2/3} +\frac{N}{\log(1/\gamma)} \log(T)\; T^{1/3} \right) | Mixed |
Closest papers by meaning
- Improved Algorithms for Contextual Dynamic Pricing (NeurIPS 2024 · similarity 0.90)
- Toward Optimal Regret in Robust Pricing: Decoupling Corruption and Time (NeurIPS 2026 · similarity 0.90)
- A Parametric Contextual Online Learning Theory of Brokerage (ICML 2025 · similarity 0.89)
- Contextual Dynamic Pricing with Heterogeneous Buyers (NeurIPS 2025 · similarity 0.88)
- Learning Safe Strategies for Value Maximizing Buyers in Uniform Price Auctions (ICML 2025 · similarity 0.88)
- Improved learning rates in multi-unit uniform price auctions (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.