Papers
Topics
Authors
Recent
Search
2000 character limit reached

New Guarantees for Learning Revenue Maximizing Menus of Lotteries and Two-Part Tariffs

Published 22 Feb 2023 in cs.GT and cs.LG | (2302.11700v3)

Abstract: We advance a recently flourishing line of work at the intersection of learning theory and computational economics by studying the learnability of two classes of mechanisms prominent in economics, namely menus of lotteries and two-part tariffs. The former is a family of randomized mechanisms designed for selling multiple items, known to achieve revenue beyond deterministic mechanisms, while the latter is designed for selling multiple units (copies) of a single item with applications in real-world scenarios such as car or bike-sharing services. We focus on learning high-revenue mechanisms of this form from buyer valuation data in both distributional settings, where we have access to buyers' valuation samples up-front, and the more challenging and less-studied online settings, where buyers arrive one-at-a-time and no distributional assumption is made about their values. We provide a suite of results with regard to these two families of mechanisms. We provide the first online learning algorithms for menus of lotteries and two-part tariffs with strong regret-bound guarantees. Since the space of parameters is infinite and the revenue functions have discontinuities, the known techniques do not readily apply. However, we are able to provide a reduction to online learning over a finite number of experts, in our case, a finite number of parameters. Furthermore, in the limited buyers type case, we show a reduction to online linear optimization, which allows us to obtain no-regret guarantees by presenting buyers with menus that correspond to a barycentric spanner. In addition, we provide algorithms with improved running times over prior work for the distributional settings. Finally, we demonstrate how techniques from the recent literature in data-driven algorithm design are insufficient for our studied problems.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (43)
  1. Nonstochastic multi-armed bandits with graph-structured feedback. SIAM J. Comput., 46(6):1785–1826, 2017. doi: 10.1137/140989455. URL https://doi.org/10.1137/140989455.
  2. Gambling in a rigged casino: The adversarial multi-armed bandit problem. In Proceedings of IEEE 36th annual foundations of computer science, pages 322–331. IEEE, 1995.
  3. Online linear optimization and adaptive routing. J. Comput. Syst. Sci., 74(1):97–114, 2008. doi: 10.1016/j.jcss.2007.04.016. URL https://doi.org/10.1016/j.jcss.2007.04.016.
  4. Adapting to a reliable network path. In Elizabeth Borowsky and Sergio Rajsbaum, editors, Proceedings of the Twenty-Second ACM Symposium on Principles of Distributed Computing, PODC 2003, Boston, Massachusetts, USA, July 13-16, 2003, pages 360–367. ACM, 2003. doi: 10.1145/872035.872090. URL https://doi.org/10.1145/872035.872090.
  5. Approximation algorithms and online mechanisms for item pricing. In Joan Feigenbaum, John C.-I. Chuang, and David M. Pennock, editors, Proceedings 7th ACM Conference on Electronic Commerce (EC-2006), Ann Arbor, Michigan, USA, June 11-15, 2006, pages 29–35. ACM, 2006. doi: 10.1145/1134707.1134711. URL https://doi.org/10.1145/1134707.1134711.
  6. Data driven semi-supervised learning. In Marc’Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan, editors, Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, pages 14782–14794, 2021. URL https://proceedings.neurips.cc/paper/2021/hash/7c93ebe873ef213123c8af4b188e7558-Abstract.html.
  7. Reducing mechanism design to algorithm design via machine learning. Journal of Computer and System Sciences, 74(8):1245–1270, 2008.
  8. Commitment without regrets: Online learning in stackelberg security games. In Tim Roughgarden, Michal Feldman, and Michael Schwarz, editors, Proceedings of the Sixteenth ACM Conference on Economics and Computation, EC ’15, Portland, OR, USA, June 15-19, 2015, pages 61–78. ACM, 2015. doi: 10.1145/2764468.2764478. URL https://doi.org/10.1145/2764468.2764478.
  9. Sample complexity of automated mechanism design. Advances in Neural Information Processing Systems, 29, 2016.
  10. Learning-theoretic foundations of algorithm configuration for combinatorial partitioning problems. In Conference on Learning Theory, pages 213–274. PMLR, 2017. URL https://arxiv.org/abs/1611.04535.
  11. Learning to branch. In International conference on machine learning, pages 344–353. PMLR, 2018a. URL https://arxiv.org/abs/1803.10150.
  12. Dispersion for data-driven algorithm design, online learning, and private optimization. In 2018 IEEE 59th Annual Symposium on Foundations of Computer Science (FOCS), pages 603–614. IEEE, 2018b.
  13. A general theory of sample complexity for multi-item profit maximization. In Proceedings of the 2018 ACM Conference on Economics and Computation, pages 173–174, 2018c.
  14. Semi-bandit optimization in the dispersed setting. In Conference on Uncertainty in Artificial Intelligence, pages 909–918. PMLR, 2020a.
  15. Efficient algorithms for learning revenue-maximizing two-part tariffs. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence,{normal-{\{{IJCAI-20}normal-}\}}, 2020b.
  16. How much data is sufficient to learn high-performing algorithms? generalization guarantees for data-driven algorithm design. In Proceedings of the 53rd Annual ACM SIGACT Symposium on Theory of Computing, pages 919–932, 2021a.
  17. Learning-to-learn non-convex piecewise-lipschitz functions. In Marc’Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan, editors, Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, pages 15056–15069, 2021b. URL https://proceedings.neurips.cc/paper/2021/hash/7ee6f2b3b68a212d3b7a4f6557eb8cc7-Abstract.html.
  18. Faster algorithms for learning to link, align sequences, and price two-part tariffs. arXiv preprint arXiv:2204.03569, 2022a.
  19. Provably tuning the elasticnet across instances. In NeurIPS, 2022b. URL http://papers.nips.cc/paper_files/paper/2022/hash/b21a34c4e8dba253f05f4a5adc68ba73-Abstract-Conference.html.
  20. Private empirical risk minimization: Efficient algorithms and tight error bounds. In 55th IEEE Annual Symposium on Foundations of Computer Science, FOCS 2014, Philadelphia, PA, USA, October 18-21, 2014, pages 464–473. IEEE Computer Society, 2014. doi: 10.1109/FOCS.2014.56. URL https://doi.org/10.1109/FOCS.2014.56.
  21. Near-optimal online auctions. In Proceedings of the Sixteenth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA 2005, Vancouver, British Columbia, Canada, January 23-25, 2005, pages 1156–1163. SIAM, 2005. URL http://dl.acm.org/citation.cfm?id=1070432.1070597.
  22. Online learning in online auctions. Theoretical Computer Science, 324(2-3):137–146, 2004.
  23. Pricing randomized allocations. In Proceedings of the twenty-first annual ACM-SIAM symposium on Discrete Algorithms, pages 585–597. SIAM, 2010.
  24. Online auctions and multi-scale online learning. In Constantinos Daskalakis, Moshe Babaioff, and Hervé Moulin, editors, Proceedings of the 2017 ACM Conference on Economics and Computation, EC ’17, Cambridge, MA, USA, June 26-30, 2017, pages 497–514. ACM, 2017. doi: 10.1145/3033274.3085145. URL https://doi.org/10.1145/3033274.3085145.
  25. Regret minimization for reserve prices in second-price auctions. IEEE Transactions on Information Theory, 61(1):549–564, 2014.
  26. The implementation of social choice rules: Some general results on incentive compatibility. The Review of Economic Studies, 46(2):185–216, 1979.
  27. The complexity of optimal mechanism design. In Proceedings of the twenty-fifth annual ACM-SIAM symposium on Discrete algorithms, pages 1302–1318. SIAM, 2014.
  28. Sampling and representation complexity of revenue maximization. In International Conference on Web and Internet Economics, pages 277–291. Springer, 2014.
  29. Optimal auctions through deep learning. In International Conference on Machine Learning, pages 1706–1715. PMLR, 2019.
  30. The sample complexity of up-to-ε𝜀\varepsilonitalic_ε multi-dimensional revenue maximization. Journal of the ACM (JACM), 68(3):1–28, 2021.
  31. Second best taxation as a game. Journal of Economic Theory, 25(1):67–91, 1981. ISSN 0022-0531. doi: https://doi.org/10.1016/0022-0531(81)90017-X. URL https://www.sciencedirect.com/science/article/pii/002205318190017X.
  32. Selling multiple correlated goods: Revenue maximization and menu-size complexity. Journal of Economic Theory, 183:991–1029, 2019.
  33. The value of knowing a demand curve: Bounds on regret for online posted-price auctions. In 44th Symposium on Foundations of Computer Science (FOCS 2003), 11-14 October 2003, Cambridge, MA, USA, Proceedings, pages 594–605. IEEE Computer Society, 2003. doi: 10.1109/SFCS.2003.1238232. URL https://doi.org/10.1109/SFCS.2003.1238232.
  34. W Arthur Lewis. The two-part tariff. Economica, 8(31):249–270, 1941.
  35. Fast algorithms for logconcave functions: Sampling, rounding, integration and optimization. In 47th Annual IEEE Symposium on Foundations of Computer Science (FOCS 2006), 21-24 October 2006, Berkeley, California, USA, Proceedings, pages 57–68. IEEE Computer Society, 2006. doi: 10.1109/FOCS.2006.28. URL https://doi.org/10.1109/FOCS.2006.28.
  36. Learning algorithms for second-price auctions with reserve. The Journal of Machine Learning Research, 17(1):2632–2656, 2016.
  37. Learning simple auctions. In Conference on Learning Theory, pages 1298–1318. PMLR, 2016.
  38. On the pseudo-dimension of nearly optimal auctions. Advances in Neural Information Processing Systems, 28, 2015.
  39. Walter Y Oi. A disneyland dilemma: Two-part tariffs for a mickey mouse monopoly. The Quarterly Journal of Economics, 85(1):77–96, 1971.
  40. Minimizing regret with multiple reserves. In Vincent Conitzer, Dirk Bergemann, and Yiling Chen, editors, Proceedings of the 2016 ACM Conference on Economics and Computation, EC ’16, Maastricht, The Netherlands, July 24-28, 2016, pages 601–616. ACM, 2016. doi: 10.1145/2940716.2940792. URL https://doi.org/10.1145/2940716.2940792.
  41. Vasilis Syrgkanis. A sample complexity measure with applications to learning optimal auctions. Advances in Neural Information Processing Systems, 30, 2017.
  42. Leslie G Valiant. A theory of the learnable. Communications of the ACM, 27(11):1134–1142, 1984.
  43. Vladimir Vapnik. Statistical Learning Theory. Wiley, 1998.
Citations (3)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up