On the Absence of Predictive Complexity for Some Games

Authors:
Yuri Kalnishkan;Michael V. Vyugin
Affiliations:
-;-
Venue:
ALT '02 Proceedings of the 13th International Conference on Algorithmic Learning Theory
Year:
2002

Citing 6
Cited 1

Aggregating strategies

COLT '90 Proceedings of the third annual workshop on Computational learning theory
Universal portfolio selection

COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
A game of prediction with expert advice

Journal of Computer and System Sciences - Special issue on the eighth annual workshop on computational learning theory, July 5–8, 1995
General linear relations between different types of predictive complexity

Theoretical Computer Science
Loss Functions, Complexities, and the Legendre Transformation

ALT '01 Proceedings of the 12th International Conference on Algorithmic Learning Theory
Mixability and the Existence of Weak Complexities

COLT '02 Proceedings of the 15th Annual Conference on Computational Learning Theory

The weak aggregating algorithm and weak mixability

Journal of Computer and System Sciences

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.