Differentiable Economics for Randomized Affine Maximizer Auctions

• URL: http://arxiv.org/abs/2202.02872v1
• Date: Sun, 6 Feb 2022 22:01:21 GMT
• Title: Differentiable Economics for Randomized Affine Maximizer Auctions
• Authors: Michael Curry, Tuomas Sandholm, John Dickerson
• Abstract summary: The ideal auction architecture for differentiable economics would be perfectly strategyproof, support multiple bidders and items, and be rich enough to represent the optimal mechanism. We present an architecture that supports multiple bidders and is perfectly strategyproof, but cannot necessarily represent the optimal mechanism. By using the gradient-based optimization tools of differentiable economics, we can now train lottery AMAs, competing with or outperforming prior approaches in revenue.
• Score: 78.08387332417604
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Optimal Automated Market Makers: Differentiable Economics and Strong Duality [22.943723387429678]
  Optimal market making in the presence of multiple goods is not well understood. We show that finding an optimal market maker is dual to an optimal transport problem. We present conjectures of optimal mechanisms in settings which show further complex behavior.
  arXiv  Detail & Related papers  (2024-02-14T12:27:54Z)
• Refined Mechanism Design for Approximately Structured Priors via Active Regression [50.71772232237571]
  We consider the problem of a revenue-maximizing seller with a large number of items for sale to $n$ strategic bidders. It is well-known that optimal and even approximately-optimal mechanisms for this setting are notoriously difficult to characterize or compute.
  arXiv  Detail & Related papers  (2023-10-11T20:34:17Z)
• A General Stochastic Optimization Framework for Convergence Bidding [0.0]
  We introduce a general optimization framework to obtain optimal convergence (virtual) bid curves. Within this framework, we develop a linear programming-based optimization model, which produces bid prices and volumes simultaneously. We show that different approximations and simplifications in the general model lead naturally to well-known convergence bidding approaches.
  arXiv  Detail & Related papers  (2022-10-12T19:14:07Z)
• Slimmable Domain Adaptation [112.19652651687402]
  We introduce a simple framework, Slimmable Domain Adaptation, to improve cross-domain generalization with a weight-sharing model bank. Our framework surpasses other competing approaches by a very large margin on multiple benchmarks.
  arXiv  Detail & Related papers  (2022-06-14T06:28:04Z)
• Learning Revenue-Maximizing Auctions With Differentiable Matching [50.62088223117716]
  We propose a new architecture to approximately learn incentive compatible, revenue-maximizing auctions from sampled valuations. Our architecture uses the Sinkhorn algorithm to perform a differentiable bipartite matching which allows the network to learn strategyproof revenue-maximizing mechanisms.
  arXiv  Detail & Related papers  (2021-06-15T04:37:57Z)
• Certifying Strategyproof Auction Networks [53.37051312298459]
  We focus on the RegretNet architecture, which can represent auctions with arbitrary numbers of items and participants. We propose ways to explicitly verify strategyproofness under a particular valuation profile using techniques from the neural network verification literature.
  arXiv  Detail & Related papers  (2020-06-15T20:22:48Z)
• Generalization Guarantees for Multi-item Profit Maximization: Pricing, Auctions, and Randomized Mechanisms [86.81403511861788]
  We study multi-item profit when there is an underlying distribution over buyers' values. For any set of buyers' values, profit is piecewise linear in the mechanism's parameters. We prove new bounds for mechanism classes not yet in the sample-based mechanism design literature.
  arXiv  Detail & Related papers  (2017-04-29T22:02:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.