PreferenceNet: Encoding Human Preferences in Auction Design with Deep Learning

• URL: http://arxiv.org/abs/2106.03215v1
• Date: Sun, 6 Jun 2021 19:29:40 GMT
• Title: PreferenceNet: Encoding Human Preferences in Auction Design with Deep Learning
• Authors: Neehar Peri, Michael J. Curry, Samuel Dooley, John P. Dickerson
• Abstract summary: We propose PreferenceNet, an extension of existing neural-network-based auction mechanisms to encode constraints. We show that our proposed method is competitive with current state-of-the-art neural-network based auction designs.
• Score: 31.509832387330928
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The design of optimal auctions is a problem of interest in economics, game theory and computer science. Despite decades of effort, strategyproof, revenue-maximizing auction designs are still not known outside of restricted settings. However, recent methods using deep learning have shown some success in approximating optimal auctions, recovering several known solutions and outperforming strong baselines when optimal auctions are not known. In addition to maximizing revenue, auction mechanisms may also seek to encourage socially desirable constraints such as allocation fairness or diversity. However, these philosophical notions neither have standardization nor do they have widely accepted formal definitions. In this paper, we propose PreferenceNet, an extension of existing neural-network-based auction mechanisms to encode constraints using (potentially human-provided) exemplars of desirable allocations. In addition, we introduce a new metric to evaluate an auction allocations' adherence to such socially desirable constraints and demonstrate that our proposed method is competitive with current state-of-the-art neural-network based auction designs. We validate our approach through human subject research and show that we are able to effectively capture real human preferences. Our code is available at https://github.com/neeharperi/PreferenceNet

Related papers

• Neural Auctions Compromise Bidder Information [43.82512707595423]
  Single-shot auctions are commonly used as a means to sell goods, for example when selling ad space or allocating radio frequencies. It has been shown that neural networks can be used to approximate optimal mechanisms while satisfying the constraints that an auction be strategyproof and individually rational. We show that despite such auctions maximizing revenue, they do so at the cost of revealing private bidder information.
  arXiv  Detail & Related papers  (2023-02-28T22:36:00Z)
• Differentiable Economics for Randomized Affine Maximizer Auctions [78.08387332417604]
  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.
  arXiv  Detail & Related papers  (2022-02-06T22:01:21Z)
• A Context-Integrated Transformer-Based Neural Network for Auction Design [25.763612577196124]
  One of the central problems in auction design is developing an incentive-compatible mechanism that maximizes the auctioneer's expected revenue. We propose $mathttCITransNet$, a context-integrated transformer-based neural network for optimal auction design. We show by extensive experiments that $mathttCITransNet$ can recover the known optimal solutions in single-item settings, outperform strong baselines in multi-item auctions, and generalize well to cases other than those in training.
  arXiv  Detail & Related papers  (2022-01-29T03:47:00Z)
• 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)
• ProportionNet: Balancing Fairness and Revenue for Auction Design with Deep Learning [55.76903822619047]
  We study the design of revenue-maximizing auctions with strong incentive guarantees. We extend techniques for approximating auctions using deep learning to address concerns of fairness while maintaining high revenue and strong incentive guarantees.
  arXiv  Detail & Related papers  (2020-10-13T13:54:21Z)
• Learning to Bid Optimally and Efficiently in Adversarial First-price Auctions [40.30925727499806]
  We develop the first minimax optimal online bidding algorithm that achieves an $widetildeO(sqrtT)$ regret. We test our algorithm on three real-world first-price auction datasets obtained from Verizon Media.
  arXiv  Detail & Related papers  (2020-07-09T05:40:39Z)
• 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)
• Auction learning as a two-player game [19.706363403596196]
  Auction Design is a two-player game with stationary utility functions. Design an incentive that maximizes expected revenue is a central problem in Auction Design.
  arXiv  Detail & Related papers  (2020-06-10T06:45:20Z)

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.