Advertisement

Preference Elicitation and Query Learning

  • Avrim Blum
  • Jeffrey C. Jackson
  • Tuomas Sandholm
  • Martin Zinkevich
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2777)

Abstract

In this paper we initiate an exploration of relationships between “preference elicitation”, a learning-style problem that arises in combinatorial auctions, and the problem of learning via queries studied in computational learning theory. Preference elicitation is the process of asking questions about the preferences of bidders so as to best divide some set of goods. As a learning problem, it can be thought of as a setting in which there are multiple target concepts that can each be queried separately, but where the goal is not so much to learn each concept as it is to produce an “optimal example”. In this work, we prove a number of similarities and differences between preference elicitation and query learning, giving both separation results and proving some connections between these problems.

Keywords

Optimal Allocation Preference Function Valuation Function Combinatorial Auction Preference Elicitation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Sandholm, T.: eMediator: A next generation electronic commerce server. Computational Intelligence 18, 656–676 (2002); Special issue on Agent Technology for Electronic Commerce, Early versions appeared in the Conference on Autonomous Agents (AGENTS 2000), pp. 73–96 (2000); AAAI 1999 Workshop on AI in Electronic Commerce, Orlando, FL, pp. 46–55 (July 1999) and as a Washington University, St. Louis, Dept. of Computer Science technical report WU-CS-99-02 (January 1999)Google Scholar
  2. 2.
    Nisan, N.: Bidding and allocation in combinatorial auctions. In: Proceedings of the ACM Conference on Electronic Commerce (ACM-EC), Minneapolis, MN, pp. 1–12 (2000)Google Scholar
  3. 3.
    Lehmann, D., O’Callaghan, L.I., Shoham, Y.: Truth revelation in rapid, approximately efficient combinatorial auctions. Journal of the ACM (2003) (to appear); Early version appeared in ACMEC 1999 (1999)Google Scholar
  4. 4.
    Conen, W., Sandholm, T.: Preference elicitation in combinatorial auctions: Extended abstract. In: Proceedings of the ACM Conference on Electronic Commerce (ACM-EC), Tampa, FL, pp. 256–259 (2001); A more detailed description of the algorithmic aspects appeared in the IJCAI-2001 Workshop on Economic Agents, Models, and Mechanisms, pp. 71–80 (2001)Google Scholar
  5. 5.
    Zinkevich, M., Blum, A., Sandholm, T.: On polynomial-time preference elicitation with value queries. In: Proceedings of the ACM Conference on Electronic Commerce (ACM-EC), San Diego, CA (2003)Google Scholar
  6. 6.
    Nisan, N., Segal, I.: The communication complexity of efficient allocation problems (2002) ( Draft. Second version March 5, 2002)Google Scholar
  7. 7.
    Rothkopf, M.H., Pekec, A., Harstad, R.M.: Computationally manageable combinatorial auctions. Management Science 44, 1131–1147 (1998)MATHCrossRefGoogle Scholar
  8. 8.
    Sandholm, T.: Algorithm for optimal winner determination in combinatorial auctions. Artificial Intelligence 135, 1–54 (2002); First appeared as an invited talk at the First International Conference on Information and Computation Economies, Charleston, SC, October 25–28 (1998), Extended version appeared asWashington Univ., Dept. of Computer Science, tech report WUCS-99-01, January 28 (1999), Conference version appeared at the International Joint Conference on Artificial Intelligence (IJCAI), Stockholm, Sweden. pp. 542–547 (1999)Google Scholar
  9. 9.
    Fujishima, Y., Leyton-Brown, K., Shoham, Y.: Taming the computational complexity of combinatorial auctions: Optimal and approximate approaches. In: Proceedings of the 16th International Joint Conference on Artificial Intelligence (IJCAI), Stockholm, Sweden, pp. 548–553 (1999)Google Scholar
  10. 10.
    Andersson, A., Tenhunen, M., Ygge, F.: Integer programming for combinatorial auction winner determination. In: Proceedings of the 4th International Conference on Multi-Agent Systems (ICMAS), Boston, MA, pp. 39–46 (2000)Google Scholar
  11. 11.
    Sandholm, T., Suri, S., Gilpin, A., Levine, D.: CABOB: A fast optimal algorithm for combinatorial auctions. In: Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence (IJCAI), Seattle, WA, pp. 1102–1108 (2001)Google Scholar
  12. 12.
    Sandholm, T.: eMediator: A next generation electronic commerce server. In: Proceedings of the 4th International Conference on Autonomous Agents (AGENTS), Barcelona, Spain, pp. 73–96 (2000); Early version appeared in the AAAI 1999 Workshop on AI in Electronic Commerce, Orlando, FL, pp. 46–55 (July 1999) and as a Washington University, St. Louis, Dept. of Computer Science technical report WU-CS-99-02 (January 1999)Google Scholar
  13. 13.
    Hoos, H., Boutilier, C.: Bidding languages for combinatorial auctions. In: Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence (IJCAI), Seattle, WA, pp. 1211–1217 (2001)Google Scholar
  14. 14.
    Sandholm, T., Suri, S.: Side constraints and non-price attributes in markets. In: IJCAI 2001 Workshop on Distributed Constraint Reasoning, Seattle, WA, pp. 55–61 (2001)Google Scholar
  15. 15.
    Conen, W., Sandholm, T.: Differential-revelation VCG mechanisms for combinatorial auctions. In: AAMAS 2002 workshop on Agent-Mediated Electronic Commerce (AMEC), Bologna, Italy (2002)Google Scholar
  16. 16.
    Hudson, B., Sandholm, T.: Effectiveness of preference elicitation in combinatorial auctions. In: AAMAS 2002 workshop on Agent-Mediated Electronic Commerce (AMEC), Bologna, Italy (2002); Extended version: Carnegie Mellon University, Computer Science Department, CMU-CS-02-124, March. Also: Stanford Institute for Theoretical Economics workshop (SITE 2002) (2002)Google Scholar
  17. 17.
    Smith, T., Sandholm, T., Simmons, R.: Constructing and clearing combinatorial exchanges using preference elicitation. In: AAAI 2002 workshop on Preferences in AI and CP: Symbolic Approaches, pp. 87–93 (2002)Google Scholar
  18. 18.
    Vickrey, W.: Counterspeculation, auctions, and competitive sealed tenders. Journal of Finance 16, 8–37 (1961)CrossRefGoogle Scholar
  19. 19.
    Clarke, E.H.: Multipart pricing of public goods. Public Choice 11, 17–33 (1971)CrossRefGoogle Scholar
  20. 20.
    Groves, T.: Incentives in teams. Econometrica 41, 617–631 (1973)MATHCrossRefMathSciNetGoogle Scholar
  21. 21.
    Parkes, D.C.: Optimal auction design for agents with hard valuation problems. In: Agent-Mediated Electronic Commerce Workshop at the International Joint Conference on Artificial Intelligence, Stockholm, Sweden (1999)Google Scholar
  22. 22.
    Parkes, D.C.: iBundle: An efficient ascending price bundle auction. In: Proceedings of the ACM Conference on Electronic Commerce (ACM-EC), Denver, CO, pp. 148–157 (1999)Google Scholar
  23. 23.
    Ausubel, L.M., Milgrom, P.: Ascending auctions with package bidding. Technical report (2001) (Draft June 7, 2001)Google Scholar
  24. 24.
    Wurman, P.R., Wellman, M.P.: AkBA: A progressive, anonymous-price combinatorial auction. In: Proceedings of the ACM Conference on Electronic Commerce (ACM-EC), Minneapolis, MN, pp. 21–29 (2000)Google Scholar
  25. 25.
    Bikhchandani, S., de Vries, S., Schummer, J., Vohra, R.V.: Linear programming and Vickrey auctions (2001) (Draft )Google Scholar
  26. 26.
    Bikhchandani, S., Ostroy, J.: The package assignment model. UCLA Working Paper Series, mimeo (2001)Google Scholar
  27. 27.
    Angluin, D., Hellerstein, L., Karpinski, M.: Learning read-once formulas with queries. Journal of the ACM 40, 185–210 (1993)MATHCrossRefMathSciNetGoogle Scholar
  28. 28.
    Angluin, D.: Queries and concept learning. Machine Learning 2, 319–342 (1988)Google Scholar
  29. 29.
    Naor, J., Naor, M.: Small-bias probability spaces: Efficient constructions and applications. In: Proc. 22nd Annual ACM Symposium on Theory of Computing, Baltimore, pp. 213–223 (1990)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Avrim Blum
    • 1
  • Jeffrey C. Jackson
    • 2
  • Tuomas Sandholm
    • 1
  • Martin Zinkevich
    • 1
  1. 1.Carnegie Mellon UniversityPittsburghUSA
  2. 2.Duquesne UniversityPittsburghUSA

Personalised recommendations