On the Absence of Predictive Complexity for Some Games
This paper shows that if the curvature of the boundary of the set of superpredictions for a game vanishes in a nontrivial way, then there is no predictive complexity for the game. This is the first result concerning the absence of complexity for games with convex sets of superpredictions. The proof is further employed to show that for some games there are no certain variants of weak predictive complexity. In the case of the absolute-loss game we reach a tight demarcation between the existing and non-existing variants of weak predictive complexity.
Unable to display preview. Download preview PDF.
- [Fel68]W. Feller. An Introduction to Probability Theory and Its Applications, volume I. John Wiley & Sons, Inc, 3rd edition, 1968.Google Scholar
- [KV02]Y. Kalnishkan and M. V. Vyugin. Mixability and the existence of weak complexities. In Jyrki Kivinen and Robert H. Sloan, editors, Computational Learning Theory, 15th Annual Conference on Computational Learning Theory, COLT 2002, Sydney, Australia, July 8-10, 2002, Proceedings, volume 2375 of Lecture Notes in Artificial Intelligence, pages 105–120. Springer, 2002.Google Scholar
- [KVV01]Y. Kalnishkan, M. Vyugin, and V. Vovk. Losses, complexities and the Legendre transformation. In Naoki Abe, Roni Khardon, and Thomas Zeugmann, editors, Proceedings of the 12th International Conference on Algorithmic Learning Theory, ALT 2001, volume 2225 of Lecture Notes in Artificial Intelligence. Springer-Verlag, 2001.Google Scholar
- [Vov90]V. Vovk. Aggregating strategies. In M. Fulk and J. Case, editors, Proceedings of the 3rd Annual Workshop on Computational Learning Theory, pages 371–383, San Mateo, CA, 1990. Morgan Kaufmann.Google Scholar
- [VW98]V. Vovk and C. J. H. C. Watkins. Universal portfolio selection. In Proceedings of the 11th Annual Conference on Computational Learning Theory, pages 12–23, 1998.Google Scholar