Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Automated Design of Affine Maximizer Mechanisms in Dynamic Settings (2402.08129v1)

Published 12 Feb 2024 in cs.GT

Abstract: Dynamic mechanism design is a challenging extension to ordinary mechanism design in which the mechanism designer must make a sequence of decisions over time in the face of possibly untruthful reports of participating agents. Optimizing dynamic mechanisms for welfare is relatively well understood. However, there has been less work on optimizing for other goals (e.g. revenue), and without restrictive assumptions on valuations, it is remarkably challenging to characterize good mechanisms. Instead, we turn to automated mechanism design to find mechanisms with good performance in specific problem instances. In fact, the situation is similar even in static mechanism design. However, in the static case, optimization/machine learning-based automated mechanism design techniques have been successful in finding high-revenue mechanisms in cases beyond the reach of analytical results. We extend the class of affine maximizer mechanisms to MDPs where agents may untruthfully report their rewards. This extension results in a challenging bilevel optimization problem in which the upper problem involves choosing optimal mechanism parameters, and the lower problem involves solving the resulting MDP. Our approach can find truthful dynamic mechanisms that achieve strong performance on goals other than welfare, and can be applied to essentially any problem setting-without restrictions on valuations-for which RL can learn optimal policies.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (62)
  1. Differentiable Convex Optimization Layers. In Neural Information Processing Systems (NeurIPS).
  2. Differentiating Through a Cone Program. arxiv:1904.09043.
  3. Altman, E. 1999. Constrained Markov decision processes, volume 7. CRC press.
  4. Repeated Contextual Auctions with Strategic Buyers. In Neural Information Processing Systems (NeurIPS).
  5. ApS, M. 2023. The MOSEK optimization toolbox, version 10.0.
  6. An efficient dynamic mechanism. Econometrica, 81(6): 2463–2485.
  7. How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design. In ACM Symposium on Theory of Computing (STOC).
  8. A general theory of sample complexity for multi-item profit maximization. In Economics and Computation (EC).
  9. Sample complexity of automated mechanism design. In Neural Information Processing Systems (NeurIPS).
  10. The dynamic pivot mechanism. Econometrica, 78(2): 771–789.
  11. Dynamic Mechanism Design: An Introduction. Journal of Economic Literature, 57(2): 235–274.
  12. Learning equilibria in symmetric auction games using artificial neural networks. Nature Machine Intelligence, 3(8): 687–695.
  13. Preference Elicitation and Query Learning. Journal of Machine Learning Research.
  14. Machine Learning-powered Iterative Combinatorial Auctions. arXiv preprint arXiv:1911.08042.
  15. Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions. In III, H. D.; and Singh, A., eds., Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, 1437–1447. PMLR.
  16. Clarke, E. H. 1971. Multipart pricing of public goods. Public Choice, 17–33.
  17. Preference Elicitation in Combinatorial Auctions: Extended Abstract. In Economics and Computation (EC), 256–259. More detailed description of algorithmic aspects in IJCAI-01 Workshop on Economic Agents, Models, and Mechanisms, pp. 71–80.
  18. Complexity of Mechanism Design. In Uncertainty in Artificial Intelligence (UAI).
  19. Incremental Mechanism Design. In International Joint Conference on Artificial Intelligence (IJCAI).
  20. Certifying Strategyproof Auction Networks. In Neural Information Processing Systems (NeurIPS).
  21. Differentiable Economics for Randomized Affine Maximizer Auctions. In International Joint Conference on Artificial Intelligence (IJCAI).
  22. Learning Revenue-Maximizing Auctions With Differentiable Matching. In International Conference on Artificial Intelligence and Statistics (AISTATS).
  23. A Scalable Neural Network for DSIC Affine Maximizer Auction Design. .
  24. Randomized smoothing for stochastic optimization. SIAM Journal on Optimization, 22(2): 674–701.
  25. Optimal Auctions through Deep Learning. In International Conference on Machine Learning (ICML).
  26. Groves, T. 1973. Incentives in teams. Econometrica: Journal of the Econometric Society, 617–631.
  27. Adaptive limited-supply online auctions. In Electronic Commerce (EC).
  28. Automated online mechanism design and prophet inequalities. In AAAI Conference on Artificial Intelligence (AAAI).
  29. Optimal-er Auctions through Attention. arXiv preprint arXiv:2202.13110.
  30. Optimal dynamic mechanism design and the virtual-pivot mechanism. Operations Research, 61(4): 837–854.
  31. Kleinberg, R. 2005. A Multiple-Choice Secretary Algorithm with Applications to Online Auctions. In Symposium on Discrete Algorithms (SODA).
  32. Enabling First-Order Gradient-Based Learning for Equilibrium Computation in Markets. arXiv preprint arXiv:2303.09500.
  33. Applying Learning Algorithms to Preference Elicitation. In Proceedings of the 5th ACM Conference on Electronic Commerce, EC ’04. New York, NY, USA: Association for Computing Machinery.
  34. Methods for boosting revenue in combinatorial auctions. In AAAI Conference on Artificial Intelligence (AAAI).
  35. JuMP 1.0: Recent improvements to a modeling language for mathematical optimization. Mathematical Programming Computation. In press.
  36. Learning Dynamic Mechanisms in Unknown Environments: A Reinforcement Learning Approach.
  37. Pessimism meets VCG: Learning Dynamic Mechanism Design via Offline Reinforcement Learning. arXiv preprint arXiv:2205.02450.
  38. Finding mixed-strategy equilibria of continuous-action games without gradients using randomized policy networks. In International Joint Conference on Artificial Intelligence (IJCAI).
  39. Myerson, R. B. 1981. Optimal auction design. Mathematics of Operations Research, 6(1): 58–73.
  40. Algorithmic Mechanism Design. Games and Economic Behavior, 35(1-2): 166–196.
  41. Algorithmic Game Theory. Cambridge University Press.
  42. Algorithmic Game Theory, chapter 16. Cambridge University Press.
  43. Optimal Dynamic Auctions. Working Paper 1461, Discussion Paper.
  44. Dynamic mechanism design: A Myersonian approach. Econometrica, 82(2): 601–653.
  45. A Permutation-Equivariant Neural Network Architecture For Auction Design. In AAAI Conference on Artificial Intelligence (AAAI).
  46. Auction learning as a two-player game. In International Conference on Learning Representations (ICLR).
  47. Roberts, K. 1979. The characterization of implementable choice rules. Aggregation and Revelation of Preferences, 12(2): 321–348.
  48. Sandholm, T. 2003. Automated mechanism design: A new application area for search algorithms. In International Conference on Principles and Practice of Constraint Programming.
  49. Preference Elicitation in Combinatorial Auctions. In Cramton, P.; Shoham, Y.; and Steinberg, R., eds., Combinatorial Auctions, 233–263. MIT Press. Chapter 10.
  50. Automated design of revenue-maximizing combinatorial auctions. Operations Research, 63(5): 1000–1025.
  51. Automated Design of Multistage Mechanisms. In International Joint Conference on Artificial Intelligence (IJCAI).
  52. Reinforcement Mechanism Design, with Applications to Dynamic Pricing in Sponsored Search Auctions. CoRR, abs/1711.10279.
  53. Automated mechanism design via neural networks. In International Conference on Autonomous Agents and MultiAgent Systems (AAMAS).
  54. Sobol’, I. 1967. On the distribution of points in a cube and the approximate evaluation of integrals. USSR Computational Mathematics and Mathematical Physics, 7(4): 86–112.
  55. Machine Learning-powered Course Allocation.
  56. On the Convergence Theory for Hessian-Free Bilevel Algorithms. In Koyejo, S.; Mohamed, S.; Agarwal, A.; Belgrave, D.; Cho, K.; and Oh, A., eds., Neural Information Processing Systems (NeurIPS).
  57. Sutton, R. S. 2018. Reinforcement learning : : an introduction. Adaptive computation and machine learning series. Cambridge, Massachusetts: The MIT Press, second edition. edition. ISBN 0-262-35270-2.
  58. Vickrey, W. 1961. Counterspeculation, auctions, and competitive sealed tenders. The Journal of Finance, 16(1): 8–37.
  59. Weed, J. 2018. An explicit analysis of the entropic penalty in linear programming. In Bubeck, S.; Perchet, V.; and Rigollet, P., eds., Proceedings of the 31st Conference On Learning Theory, volume 75 of Proceedings of Machine Learning Research, 1841–1855. PMLR.
  60. Bayesian Optimization-based Combinatorial Assignment. arXiv preprint arXiv:2208.14698.
  61. Yao, A. C.-C. 2017. Dominant-strategy versus bayesian multi-item auctions: Maximum revenue determination and comparison. In Economics and Computation (EC).
  62. On Polynomial-Time Preference Elicitation with Value Queries. In Economics and Computation (EC), 176–185.
Citations (4)

Summary

We haven't generated a summary for this paper yet.