Conformalized Strategy-Proof Auctions (2405.12016v4)
Abstract: Auctions are key for maximizing sellers' revenue and ensuring truthful bidding among buyers. Recently, an approach known as differentiable economics based on ML has shown promise in learning powerful auction mechanisms for multiple items and participants. However, this approach has no guarantee of strategy-proofness at test time. Strategy-proofness is crucial as it ensures that buyers are incentivized to bid their true valuations, leading to optimal and fair auction outcomes without the risk of manipulation. In this work, we propose a formulation of statistical strategy-proofness auction mechanism, ensuring that the probability of regret exceeding a predefined threshold is strictly controlled. Building upon conformal prediction techniques, we develop an auction acceptance rule that leverages regret predictions to guarantee that the data-driven auction mechanism meets the statistical strategy-proofness requirement with high probability. Our approach represents a practical middle-ground between two extremes: forcing zero-regret at the cost of significant revenue loss, and naively using ML to construct auctions with the hope of attaining low regret at test time. Numerical experiments demonstrate the necessity of the proposed method, the validity of our theoretical result, and its applicability.
- Conformal prediction: A gentle introduction. Foundations and Trends® in Machine Learning, 16(4):494–591, 2023.
- Conformal prediction beyond exchangeability. The Annals of Statistics, 51(2):816–845, 2023.
- Certifying strategyproof auction networks. Advances in Neural Information Processing Systems, 33:4987–4998, 2020.
- Differentiable economics for randomized affine maximizer auctions. In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, pages 2633–2641, 2023.
- Strong duality for a multiple-good monopolist. In Proceedings of the Sixteenth ACM Conference on Economics and Computation, pages 449–450, 2015.
- A scalable neural network for DSIC affine maximizer auction design. Advances in Neural Information Processing Systems, 36, 2023.
- Payment rules through discriminant-based classifiers, 2015.
- Optimal auctions through deep learning. In International Conference on Machine Learning, pages 1706–1715. PMLR, 2019.
- Optimal auctions through deep learning: Advances in differentiable economics. Journal of the ACM, 71(1):1–53, 2024.
- Optimal-er auctions through attention. Advances in Neural Information Processing Systems, 35:34734–34747, 2022.
- Optimal auctions with restricted allocations. In Proceedings of the 2016 ACM Conference on Economics and Computation, pages 215–232, 2016.
- V. Krishna. Auction theory. Academic press, 2009.
- J. Lei and L. Wasserman. Distribution-free prediction bands for non-parametric regression. Journal of the Royal Statistical Society Series B: Statistical Methodology, 76(1):71–96, 2014.
- Bundling as an optimal selling mechanism for a multiple-good monopolist. Journal of Economic Theory, 127(1):1–35, 2006.
- P. R. Milgrom. Putting auction theory to work. Cambridge University Press, 2004.
- R. B. Myerson. Optimal auction design. Mathematics of operations research, 6(1):58–73, 1981.
- Inductive confidence machines for regression. In Machine learning: ECML 2002: 13th European conference on machine learning Helsinki, Finland, August 19–23, 2002 proceedings 13, pages 345–356. Springer, 2002.
- G. Pavlov. Optimal mechanism for selling two goods. The BE Journal of Theoretical Economics, 11(1):0000102202193517041664, 2011.
- Preferencenet: Encoding human preferences in auction design with deep learning. Advances in Neural Information Processing Systems, 34:17532–17542, 2021.
- A permutation-equivariant neural network architecture for auction design. In Proceedings of the AAAI conference on artificial intelligence, volume 35, pages 5664–5672, 2021a.
- Auction learning as a two-player game. In International Conference on Learning Representations, 2021b.
- K. Roberts. The characterization of implementable choice rules. Aggregation and revelation of preferences, 12(2):321–348, 1979.
- Neural auctions compromise bidder information. arXiv preprint arXiv:2303.00116, 2023.
- Machine-learning applications of algorithmic randomness. In International Conference on Machine Learning, pages 444–453, 1999.
- Algorithmic learning in a random world, volume 29. Springer, 2005.
- A. C.-C. Yao. Dominant-strategy versus bayesian multi-item auctions: Maximum revenue determination and comparison. In Proceedings of the 2017 ACM Conference on Economics and Computation, pages 3–20, 2017.