Research map / Learning theory and algorithms / Submodular and game algorithms
Optimal Auctions through Deep Learning
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 |
|---|---|---|---|
| compare learned auction to analytical optimum, additive single bidder | RegretNet · (I) | revenue: 0.550 -> 0.554 | No clear effect |
| compare to analytical optimum, unit-demand single bidder | RegretNet · (II) | revenue: 2.137 -> 2.137 | No clear effect |
| replace VVCA/AMAbsym auctions with learned RegretNet | RegretNet · (III) | revenue: 0.862 -> 0.878 | Helped |
| replace VVCA/AMAbsym with RegretNet | RegretNet · (IV) | revenue: 2.765 -> 2.871 | Helped |
| replace VVCA/AMAbsym with RegretNet | RegretNet · (V) | revenue: 4.209 -> 4.270 | Helped |
| replace item-wise Myerson with RegretNet at scale | RegretNet · (VI) 3 bidders 10 items | revenue: 5.310 -> 5.541 | Helped |
| replace item-wise Myerson with RegretNet at scale | RegretNet · (VII) 5 bidders 10 items | revenue: 6.716 -> 6.778 | Helped |
| replace bundled Myerson with RegretNet | RegretNet · (VII) | revenue: 5.453 -> 6.778 | Helped |
| replace LP (5 bins) with RegretNet on regret | RegretNet · 2x3 additive | regret: 0.019 -> < 0.001 | Helped |
| replace LP with RegretNet on run-time | RegretNet · 2x3 additive | run-time: 69 hrs -> ∼9 hrs | Helped |
| replace LP with RegretNet on revenue | RegretNet · 2x3 additive | revenue: 1.53 -> 1.291 | Hurt |
| vary architecture depth/width (more layers or nodes) (ablation) | RegretNet · held-out validation | revenue | No clear effect |
Closest papers by meaning
- BundleFlow: Deep Menus for Combinatorial Auctions by Diffusion-Based Optimization (NeurIPS 2025 · similarity 0.91)
- Learning Optimal Auctions with Correlated Value Distributions (AAAI 2025 · similarity 0.90)
- Auctionformer: A Unified Deep Learning Algorithm for Solving Equilibrium Strategies in Auction Games (ICML 2024 · similarity 0.90)
- Increasing Revenue in Efficient Combinatorial Auctions by Learning to Generate Artificial Competition (AAAI 2025 · similarity 0.89)
- AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Games (NeurIPS 2024 · similarity 0.88)
- Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them All (ICML 2025 · similarity 0.88)
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.