mlsanityData to 7 Oct 2026

Differentiable Economics for Randomized Affine Maximizer Auctions

arXiv 2202.02872 ↗First posted 6 Feb 2022cs.GT cs.LG econ.GNcited by 21

Not on the map. Why?

Abstract (arXiv)

A recent approach to automated mechanism design, differentiable economics, represents auctions by rich function approximators and optimizes their performance by gradient descent. The ideal auction architecture for differentiable economics would be perfectly strategyproof, support multiple bidders and items, and be rich enough to represent the optimal (i.e. revenue-maximizing) mechanism. So far, such an architecture does not exist. There are single-bidder approaches (MenuNet, RochetNet) which are always strategyproof and can represent optimal mechanisms. RegretNet is multi-bidder and can approximate any mechanism, but is only approximately strategyproof. We present an architecture that supports multiple bidders and is perfectly strategyproof, but cannot necessarily represent the optimal mechanism. This architecture is the classic affine maximizer auction (AMA), modified to offer lotteries. By using the gradient-based optimization tools of differentiable economics, we can now train lottery AMAs, competing with or outperforming prior approaches in revenue.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 27 of its 76 references that are in the map. First posted on arXiv 6 Feb 2022.

Builds on

27 of 76 references.

References · 27

  1. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,250
  2. 2014Complexity of Mechanism Designcited by 33
  3. 2018Automated Mechanism Design via Neural Networkscited by 31
  4. 2020A Permutation-Equivariant Neural Network Architecture For Auction Designcited by 31
  5. 2020Auction learning as a two-player gamecited by 29
  6. 2019How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm designcited by 27
  7. 2016Sample Complexity of Automated Mechanism Designcited by 24
  8. 2021PreferenceNet: Encoding Human Preferences in Auction Design with Deep Learningcited by 22
  9. 2020Certifying Strategyproof Auction Networkscited by 21
  10. 2020ProportionNet: Balancing Fairness and Revenue for Auction Design with Deep Learningcited by 19
  11. 2021Towards Efficient Auctions in an Auto-bidding Worldcited by 19
  12. 2022A Context-Integrated Transformer-Based Neural Network for Auction Designcited by 19
15 more
  1. 2014Strong Duality for a Multiple-Good Monopolistcited by 17
  2. 2021Deep Learning for Two-Sided Matchingcited by 15
  3. 2021Learning Revenue-Maximizing Auctions With Differentiable Matchingcited by 14
  4. 2019Deep Learning-powered Iterative Combinatorial Auctionscited by 12
  5. 2013Understanding Incentives: Mechanism Design becomes Algorithm Designcited by 10
  6. 2019Machine Learning-powered Iterative Combinatorial Auctionscited by 10
  7. 2018A Duality-Based Unified Approach to Bayesian Mechanism Designcited by 9
  8. 2014An n-to-1 Bidder Reduction for Multi-item Auctions and its Applicationscited by 7
  9. 2016Optimal Auctions with Restricted Allocationscited by 7
  10. 2020Fourier Analysis-based Iterative Combinatorial Auctionscited by 7
  11. 2016Simple Mechanisms for Subadditive Buyers via Dualitycited by 6
  12. 2020Reinforcement Learning of Sequential Price Mechanismscited by 6
  13. 2013Selling Multiple Correlated Goods: Revenue Maximization and Menu-Size Complexity (old title: "The Menu-Size Complexity of Auctions")cited by 4
  14. 2018Fast Iterative Combinatorial Auctions via Bayesian Learningcited by 4
  15. 2020Optimizing Affine Maximizer Auctions via Linear Programming: an Application to Revenue Maximizing Mechanism Design for Zero-Day Exploits Marketscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 5; 2024: 7; 2025: 3; 2026: 5.

21 papers.

Sort:

By area:

  1. 2022Optimal-er Auctions through Attentioncited by 26
  2. 2023A Scalable Neural Network for DSIC Affine Maximizer Auction Designcited by 23
  3. 2024GemNet: Menu-Based, Strategy-Proof Multi-Bidder Auctions Through Deep Learningcited by 14
  4. 2023Data Market Design through Deep Learningcited by 7
  5. 2023Mode Connectivity in Auction Designcited by 3
  6. 2024Automated Deterministic Auction Design with Objective Decompositioncited by 2
  7. 2025Aligned Textual Scoring Rulescited by 2
  8. 2023Neural Auctions Compromise Bidder Informationcited by 1
  9. 2024Optimal Automated Market Makers: Differentiable Economics and Strong Dualitycited by 1
  10. 2026Bridging the Gap Between Estimated and True Regret Towards Reliable Regret Estimation in Deep Learning based Mechanism Designcited by 1
  11. 2026Incentive-Aware Multi-Fidelity Optimization for Generative Advertising in Large Language Modelscited by 1
  12. 2023Mechanism Design for Ad Auctions with Display Pricescited by 0
9 more
  1. 2024Statistically Truthful Auctions via Acceptance Rulecited by 0
  2. 2024Large-Scale Contextual Market Equilibrium Computation through Deep Learningcited by 0
  3. 2024Learning Fair and Preferable Allocations through Neural Networkcited by 0
  4. 2024Learning Neural Strategy-Proof Matching Mechanism from Examplescited by 0
  5. 2025Optimal Auction Design in the Joint Advertisingcited by 0
  6. 2025Universal Representation of Generalized Convex Functions and their Gradientscited by 0
  7. 2026LLM Active Alignment: A Nash Equilibrium Perspectivecited by 0
  8. 2026Enhancing Affine Maximizer Auctions with Correlation-Aware Paymentcited by 0
  9. 2026Duality for Optimal Multi-Item, Multi-Bidder Auction Design: Revenue Certificates through Deep Learningcited by 0