Corpus ID: 235358890

PreferenceNet: Encoding Human Preferences in Auction Design with Deep Learning

@article{Peri2021PreferenceNetEH,
  title={PreferenceNet: Encoding Human Preferences in Auction Design with Deep Learning},
  author={Neehar Peri and Michael J. Curry and Samuel Dooley and John P. Dickerson},
  journal={ArXiv},
  year={2021},
  volume={abs/2106.03215}
}
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… Expand

Figures and Tables from this paper

A Survey of Online Auction Mechanism Design Using Deep Learning Approaches
  • Zhanhao Zhang
  • Computer Science
  • ArXiv
  • 2021
TLDR
Some common deep learning infrastructures adopted in auction mechanism designs and how these architectures are evolving are summarized and pointed out several currently unresolved issues for future directions. Expand
Learning Revenue-Maximizing Auctions With Differentiable Matching
TLDR
This work proposes a new architecture that uses the Sinkhorn algorithm to perform a differentiable bipartite matching which allows the network to learn strategyproof revenue-maximizing mechanisms in settings not learnable by the previous RegretNet architecture. Expand

References

SHOWING 1-10 OF 53 REFERENCES
Multi-category fairness in sponsored search auctions
TLDR
This work proposes inter-category and intra-category fairness desiderata that take inspiration from individual fairness and envy-freeness, and investigates the "platform utility" achievable by mechanisms satisfying these desidersata. Expand
Automated Mechanism Design via Neural Networks
TLDR
This paper puts forward a unified neural network based framework that automatically learns to design revenue optimal mechanisms and theoretically proves that the mechanisms found by the framework are indeed optimal. Expand
Optimal auctions through deep learning
TLDR
This work overviews recent research results that show how tools from deep learning are shaping up to become a powerful tool for the automated design of near-optimal auctions auctions and recovers to a high degree of accuracy essentially all known analytically derived solutions for multi-item settings. Expand
ProportionNet: Balancing Fairness and Revenue for Auction Design with Deep Learning
TLDR
Techniques for approximating auctions using deep learning are extended to address concerns of fairness while maintaining high revenue and strong incentive guarantees. Expand
A Permutation-Equivariant Neural Network Architecture For Auction Design
TLDR
It is demonstrated that permutation-equivariant architectures are not only capable of recovering previous results, they also have better generalization properties, which is not possible with the previous architecture. Expand
Auction learning as a two-player game
TLDR
This work uses recent results in theoretical auction design to introduce a time-independent Lagrangian, which circumvents the need for an expensive hyper-parameter search, and provides a principled metric to compare the performance of two auctions. Expand
Learning to Generate Fair Clusters from Demonstrations
TLDR
An algorithm to identify the fairness metric from demonstrations and generate clusters using existing off-the-shelf clustering techniques, and a greedy method for clustering for novel fairness metrics for which clustering algorithms do not currently exist are presented. Expand
Certifying Strategyproof Auction Networks
TLDR
This work proposes ways to explicitly verify strategyproofness under a particular valuation profile using techniques from the neural network verification literature, and trains the network and produces certificates in several settings, including settings for which the optimal strategyproof mechanism is not known. Expand
Fairness in ad auctions through inverse proportionality
TLDR
A new class of allocation algorithms called Inverse Proportional Allocation that achieve value stability with respect to an expressive class of stability conditions and extend the results to broader notions of fairness that are called subset fairness. Expand
Measuring Non-Expert Comprehension of Machine Learning Fairness Metrics
TLDR
A metric to measure comprehension of three such definitions of fairness in machine learning--demographic parity, equal opportunity, and equalized odds is developed. Expand
...
1
2
3
4
5
...