Auction learning as a two-player game

• URL: http://arxiv.org/abs/2006.05684v4
• Date: Mon, 25 Oct 2021 15:45:41 GMT
• Title: Auction learning as a two-player game
• Authors: Jad Rahme and Samy Jelassi and S. Matthew Weinberg
• Abstract summary: 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.
• Score: 19.706363403596196
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Designing an incentive compatible auction that maximizes expected revenue is a central problem in Auction Design. While theoretical approaches to the problem have hit some limits, a recent research direction initiated by Duetting et al. (2019) consists in building neural network architectures to find optimal auctions. We propose two conceptual deviations from their approach which result in enhanced performance. First, we use recent results in theoretical auction design (Rubinstein and Weinberg, 2018) to introduce a time-independent Lagrangian. This not only circumvents the need for an expensive hyper-parameter search (as in prior work), but also provides a principled metric to compare the performance of two auctions (absent from prior work). Second, the optimization procedure in previous work uses an inner maximization loop to compute optimal misreports. We amortize this process through the introduction of an additional neural network. We demonstrate the effectiveness of our approach by learning competitive or strictly improved auctions compared to prior work. Both results together further imply a novel formulation of Auction Design as a two-player game with stationary utility functions.

Related papers

• Procurement Auctions via Approximately Optimal Submodular Optimization [53.93943270902349]
  We study procurement auctions, where an auctioneer seeks to acquire services from strategic sellers with private costs. Our goal is to design computationally efficient auctions that maximize the difference between the quality of the acquired services and the total cost of the sellers.
  arXiv  Detail & Related papers  (2024-11-20T18:06:55Z)
• Selling Joint Ads: A Regret Minimization Perspective [7.288063443108292]
  Motivated by online retail, we consider the problem of selling one item (e.g., an ad slot) to two non-excludable buyers (say, a merchant and a brand) This problem captures, for example, situations where a merchant and a brand bid cooperatively in an auction to advertise a product, and both benefit from the ad being shown. A mechanism collects bids from the two and decides whether to allocate and which payments the two parties should make.
  arXiv  Detail & Related papers  (2024-09-12T07:59:10Z)
• Neural Active Learning Beyond Bandits [69.99592173038903]
  We study both stream-based and pool-based active learning with neural network approximations. We propose two algorithms based on the newly designed exploitation and exploration neural networks for stream-based and pool-based active learning.
  arXiv  Detail & Related papers  (2024-04-18T21:52:14Z)
• Machine Learning-Powered Combinatorial Clock Auction [13.724491757145385]
  We study the design of iterative auctions (ICAs) We present a novel method for training an ML model on demand queries. We experimentally evaluate our ML-based demand mechanism in several spectrum auction domains.
  arXiv  Detail & Related papers  (2023-08-20T10:43:50Z)
• Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games [66.2085181793014]
  We show that a model-free stage-based Q-learning algorithm can enjoy the same optimality in the $H$ dependence as model-based algorithms. Our algorithm features a key novel design of updating the reference value functions as the pair of optimistic and pessimistic value functions.
  arXiv  Detail & Related papers  (2023-08-17T08:34:58Z)
• Autobidders with Budget and ROI Constraints: Efficiency, Regret, and Pacing Dynamics [53.62091043347035]
  We study a game between autobidding algorithms that compete in an online advertising platform. We propose a gradient-based learning algorithm that is guaranteed to satisfy all constraints and achieves vanishing individual regret.
  arXiv  Detail & Related papers  (2023-01-30T21:59:30Z)
• Improved Algorithms for Neural Active Learning [74.89097665112621]
  We improve the theoretical and empirical performance of neural-network(NN)-based active learning algorithms for the non-parametric streaming setting. We introduce two regret metrics by minimizing the population loss that are more suitable in active learning than the one used in state-of-the-art (SOTA) related work.
  arXiv  Detail & Related papers  (2022-10-02T05:03:38Z)
• Bayesian Optimization-based Combinatorial Assignment [10.73407470973258]
  We study the assignment domain, which includes auctions and course allocation. The main challenge in this domain is that the bundle space grows exponentially in the number of items.
  arXiv  Detail & Related papers  (2022-08-31T08:47:02Z)
• Fast Rate Learning in Stochastic First Price Bidding [0.0]
  First-price auctions have largely replaced traditional bidding approaches based on Vickrey auctions in programmatic advertising. We show how to achieve significantly lower regret when the opponents' maximal bid distribution is known. Our algorithms converge much faster than alternatives proposed in the literature for various bid distributions.
  arXiv  Detail & Related papers  (2021-07-05T07:48:52Z)
• PreferenceNet: Encoding Human Preferences in Auction Design with Deep Learning [31.509832387330928]
  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.
  arXiv  Detail & Related papers  (2021-06-06T19:29:40Z)
• 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)

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.