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

Subsidy design for better social outcomes (2409.03129v1)

Published 4 Sep 2024 in cs.GT and cs.LG

Abstract: Overcoming the impact of selfish behavior of rational players in multiagent systems is a fundamental problem in game theory. Without any intervention from a central agent, strategic users take actions in order to maximize their personal utility, which can lead to extremely inefficient overall system performance, often indicated by a high Price of Anarchy. Recent work (Lin et al. 2021) investigated and formalized yet another undesirable behavior of rational agents, that of avoiding freely available information about the game for selfish reasons, leading to worse social outcomes. A central planner can significantly mitigate these issues by injecting a subsidy to reduce certain costs associated with the system and obtain net gains in the system performance. Crucially, the planner needs to determine how to allocate this subsidy effectively. We formally show that designing subsidies that perfectly optimize the social good, in terms of minimizing the Price of Anarchy or preventing the information avoidance behavior, is computationally hard under standard complexity theoretic assumptions. On the positive side, we show that we can learn provably good values of subsidy in repeated games coming from the same domain. This data-driven subsidy design approach avoids solving computationally hard problems for unseen games by learning over polynomially many games. We also show that optimal subsidy can be learned with no-regret given an online sequence of games, under mild assumptions on the cost matrix. Our study focuses on two distinct games: a Bayesian extension of the well-studied fair cost-sharing game, and a component maintenance game with engineering applications.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (48)
  1. Neural network learning: Theoretical foundations. Cambridge University Press, 1999.
  2. Computational complexity: a modern approach. Cambridge University Press, 2009.
  3. The price of stability for network design with fair cost allocation. SIAM Journal on Computing, 38(4):1602–1623, 2008.
  4. AT Ajekigbe. Fear of mastectomy: the most common factor responsible for late presentation of carcinoma of the breast in nigeria. Clinical Oncology, Royal College of Radiologists (RCR), 3(2):78–80, 1991.
  5. Maria Florina Balcan. Leading dynamics to good behavior. ACM SIGecom Exchanges, 10(2):19–22, 2011.
  6. Maria-Florina Balcan. Data-Driven Algorithm Design (book chapter). In Beyond Worst Case Analysis of Algorithms, Tim Roughgarden (Ed). Cambridge University Press, 2020.
  7. Improved equilibria via public service advertising. In Proceedings of the twentieth annual ACM-SIAM symposium on Discrete algorithms, pages 728–737. SIAM, 2009.
  8. The price of uncertainty. In Proceedings of the 10th ACM conference on Electronic commerce, pages 285–294, 2009.
  9. Circumventing the price of anarchy: Leading dynamics to good behavior. SIAM Journal on Computing, 42(1):230–264, 2013.
  10. An analysis of robustness of non-Lipschitz networks. Journal of Machine Learning Research (JMLR), 24(98):1–43, 2023.
  11. Semi-bandit optimization in the dispersed setting. In Conference on Uncertainty in Artificial Intelligence (UAI), pages 909–918. PMLR, 2020.
  12. Learning piecewise Lipschitz functions in changing environments. In International Conference on Artificial Intelligence and Statistics (AISTATS), pages 3567–3577. PMLR, 2020.
  13. 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, 2018.
  14. Data-driven clustering via parameterized lloyd’s families. Advances in Neural Information Processing Systems (NeurIPS), 31, 2018.
  15. Provably tuning the elasticnet across instances. Advances in Neural Information Processing Systems (NeurIPS), 35:27769–27782, 2022.
  16. Non-cooperative cost sharing games via subsidies. In International Symposium on Algorithmic Game Theory (SAGT), pages 337–349. Springer, 2008.
  17. New bounds for hyperparameter tuning of regression problems across instances. Advances in Neural Information Processing Systems (NeurIPS), 36, 2023.
  18. Learning-theoretic foundations of algorithm configuration for combinatorial partitioning problems. In Conference on Learning Theory (COLT), pages 213–274. PMLR, 2017.
  19. Data driven semi-supervised learning. Advances in Neural Information Processing Systems (NeurIPS), 34:14782–14794, 2021.
  20. Learning accurate and interpretable decision trees. Conference on Uncertainty in Artificial Intelligence (UAI), 2024.
  21. Output-sensitive erm-based techniques for data-driven algorithm design. arXiv preprint arXiv:2204.03569, 2022.
  22. A general theory of sample complexity for multi-item profit maximization. In Proceedings of the 2018 ACM Conference on Economics and Computation (EC), pages 173–174, 2018.
  23. Prediction, learning, and games. Cambridge university press, 2006.
  24. Non-cooperative multicast and facility location games. In Proceedings of the 7th ACM conference on Electronic commerce, pages 72–81, 2006.
  25. Online multicast with egalitarian cost sharing. In Proceedings of the twentieth annual symposium on Parallelism in algorithms and architectures, pages 70–76, 2008.
  26. Fundamentals of parameterized complexity, volume 4. Springer, 2013.
  27. The effectiveness of subsidies and tolls in congestion games. IEEE Transactions on Automatic Control, 67(6):2729–2742, 2021.
  28. Information avoidance. Journal of Economic Literature (JEL), 55(1):96–135, 2017.
  29. A PAC approach to application-specific algorithm selection. In Proceedings of the 2016 ACM Conference on Innovations in Theoretical Computer Science, pages 123–134, 2016.
  30. Richard M Karp. Reducibility among combinatorial problems (book chapter). In Complexity of Computer Computations, R. E. Miller and J. W. Thatcher (Eds), 1972.
  31. Inducing equilibria in networked public goods games through network structure modification. In Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems, pages 611–619, 2020.
  32. Multi-agent value of information for components’ inspections. The 13th International Conference on Structural Safety and Reliability (ICOSSAR), 2021.
  33. Minimal subsidies in expense sharing games. In International Symposium on Algorithmic Game Theory (SAGT), pages 347–358. Springer, 2010.
  34. Value of information for spatially distributed systems: Application to sensor placement. Reliability Engineering and System Safety, 154:219–233, 2016.
  35. Value of information in sequential decision making: Component inspection, permanent monitoring and system-level scheduling. Reliability Engineering & System Safety, 154:137–151, 2016.
  36. On the pseudo-dimension of nearly optimal auctions. Advances in Neural Information Processing Systems (NeurIPS), 28, 2015.
  37. Foundations of machine learning. MIT press, 2018.
  38. Algorithmic game theory. Cambridge University Press, 2007.
  39. Information avoidance and overvaluation under epistemic constraints: Principles and implications for regulatory policies. Reliability Engineering & System Safety, 197:106814, 2020.
  40. David Pollard. Convergence of stochastic processes. Springer Science & Business Media, 2012.
  41. Tim Roughgarden. The price of anarchy in games of incomplete information. In Proceedings of the 13th ACM Conference on Electronic Commerce (EC), pages 862–879, 2012.
  42. Applied statistical decision theory. 1961.
  43. Dravyansh Sharma. Data-driven algorithm design and principled hyperparameter tuning in machine learning. PhD thesis, Carnegie Mellon University, 2024.
  44. Information avoidance: Who, what, when, and why. Review of general psychology, 14(4):340–353, 2010.
  45. How people decide what they want to know. Nature Human Behaviour, 4(1):14–19, 2020.
  46. On the uniform convergence of relative frequencies of events to their probabilities. Theory of Probability and its Applications, 16(2):264, 1971.
  47. Steering no-regret learners to optimal equilibria. arXiv preprint arXiv:2306.05221, 2023.
  48. Taxation and stability in cooperative games. In Proceedings of the 2013 International conference on Autonomous agents and Multi-agent Systems (AAMAS), pages 523–530, 2013.
Citations (1)
View on Semantic Scholar

Summary

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

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now