Mixability and the Existence of Weak Complexities
This paper investigates the behaviour of the constant c(β) from the Aggregating Algorithm. Some conditions for mixability are derived and it is shown that for many non-mixable games c(β) still converges to 1. The condition c(β) → 1 is shown to imply the existence of weak predictive complexity and it is proved that many games specify complexity up to √n.
KeywordsLoss Function Expert Advice Canonical Representation Weak Complexity Computational Learn Theory
Unable to display preview. Download preview PDF.
- [KVV01]Y. Kalnishkan, M. Vyugin, and V. Vovk. Losses, complexities and the Legendre transformation. In 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
- [V’y00]V. V. V’yugin. Sub-optimal measures of predictive complexity for absolute loss function. Technical Report CLRC TR-00-05, Computer Learning Research Centre, Royal Holloway College, University of London, 2000.Google Scholar