Non-linear Inequalities between Predictive and Kolmogorov ComplexitiesAuthors: Michael V. Vyugin and Vladimir V. V'yugin. Source: Lecture Notes in Artificial Intelligence Vol. 2225, 2001, 190 - 204. Abstract. Predictive complexity is a generalization of Kolmogorov complexity. It corresponds to an "optimal" prediction strategy which gives a lower bound to ability of any algorithm to predict elements of a sequence of outcomes. A variety of types of loss functions makes it interesting to study relations between corresponding predictive complexities.
Non-linear inequalities (with variable coefficients)
between predictive complexity
©Copyright 2001 Springer |