Research map / Bandits and online learning / Online convex optimization and games
Learning to Bid in Repeated First-Price Auctions with Budgets
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 |
|---|---|---|---|
| Budget control via dual variable lambda (value shading by 1+lambda) added to bidding | First-price auction bidder, full and one-sided feedback · Simulated first-price auctions (T=10^6, B=10^4, normal/log-normal/uniform values) | reward per round | Helped |
| Value shading and bid elimination for one-sided feedback | One-sided information feedback algorithm · Simulated uniform values U(0.25,1) | regret bound growth | No clear effect |
Closest papers by meaning
- Coordinated Dynamic Bidding in Repeated Second-Price Auctions with Budgets (ICML 2023 · similarity 0.93)
- Dynamic Budget Throttling in Repeated Second-Price Auctions (AAAI 2024 · similarity 0.91)
- No-Regret Online Autobidding Algorithms in First-price Auctions (NeurIPS 2025 · similarity 0.91)
- Comparing Uniform Price and Discriminatory Multi-Unit Auctions through Regret Minimization (NeurIPS 2025 · similarity 0.87)
- Non-stochastic Budgeted Online Pricing with Semi-Bandit Feedback (AAAI 2025 · similarity 0.87)
- Learning Safe Strategies for Value Maximizing Buyers in Uniform Price Auctions (ICML 2025 · 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.