A new family of boosting algorithms, denoted TaylorBoost, is proposed. It supports any combination of loss function and first or second order optimization, and includes classical...
Mohammad Saberian, Hamed Masnadi-Shirazi, Nuno Vas...
A general technique is proposed to deal with the formalization of intuition and human-oriented concepts in competition thinking games like chess, such as defensive play, attack, t...
Abstract. We propose an extensive-form game as a model for pricing roaming charges in 802.11 wireless data networks. We specify utility functions for the three agents involved in t...
Belief merging is concerned with the integration of several belief bases such that a coherent belief base is developed. Various belief merging models have been developed that use a...
Min-max functions are dynamic programming operators of zero-sum deterministic games with finite state and action spaces. The problem of computing the linear growth rate of the or...