Research map / Learning theory and algorithms / Submodular and game algorithms
Data Market Design through Deep Learning
Sai Srivatsa Ravindranath, Yanchen Jiang, David C. Parkes
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 |
|---|---|---|---|
| learn menu with RochetNet instead of using theory-derived optimal menu | RochetNet · Single buyer Setting A | revenue: 0.125 -> 0.125 | No clear effect |
| learn menu with RochetNet instead of using theory-derived optimal menu | RochetNet · Single buyer Setting B | revenue: 0.166 -> 0.167 | No clear effect |
| use RegretNet instead of analytical optimal mechanism | RegretNet · BIC UNF alpha=0.5 theta=(0.5, 0.5) | test revenue: 0.395 -> 0.400 | No clear effect |
| use RegretNet instead of analytical optimal mechanism | RegretNet · BIC EXP alpha=2.0 theta=(0.75, 0.25) | test revenue: 1.415 -> 1.390 | Hurt |
| use RegretNet instead of analytical optimal mechanism | RegretNet · BIC EXP alpha=2.0 theta=(0.5, 0.5) | test revenue: 1.613 -> 1.603 | No clear effect |
| use RegretNet instead of analytical optimal mechanism | RegretNet · BIC UNF alpha=2.0 theta=(0.5, 0.5) | test revenue: 1.042 -> 1.056 | No clear effect |
| increase negative externality intensity alpha from 0.5 to 2.0 | RegretNet · BIC UNF theta=(0.5, 0.5) | test revenue: 0.400 -> 1.056 | Improved |
| increase negative externality intensity alpha from 0.5 to 2.0 | RegretNet · BIC EXP theta=(0.5, 0.5) | test revenue: 0.632 -> 1.603 | Improved |
| increase negative externality intensity alpha from 0.5 to 2.0 | RegretNet · BIC Asym UNF theta=(0.5, 0.5) | test revenue: 0.614 -> 1.599 | Improved |
| raise lower payoff bound c in Setting D above 0.55 (ablation) | RochetNet · Single buyer Setting D | menu structure: c < 0.55 | Mixed |
| increase frequency of high type in the prior mixture (Experiment G) (ablation) | RochetNet · Single buyer Experiment G | differential informativeness q | Mixed |
Closest papers by meaning
- BundleFlow: Deep Menus for Combinatorial Auctions by Diffusion-Based Optimization (NeurIPS 2025 · similarity 0.85)
- Auctionformer: A Unified Deep Learning Algorithm for Solving Equilibrium Strategies in Auction Games (ICML 2024 · similarity 0.84)
- Learning to Price Homogeneous Data (NeurIPS 2024 · similarity 0.84)
- Increasing Revenue in Efficient Combinatorial Auctions by Learning to Generate Artificial Competition (AAAI 2025 · similarity 0.84)
- An Instrumental Value for Data Production and its Application to Data Pricing (ICML 2025 · similarity 0.84)
- Non-Linear Pricing Restores Tractability for a Data Seller (NeurIPS 2026 · similarity 0.84)
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.
