We consider multi-agent systems whose agents compete for resources by striving to be in the minority group. The agents adapt to the environment by reinforcement learning of the pr...
In this paper, we use the rollout method for policy improvement to analyze a version of Klondike solitaire. This version, sometimes called thoughtful solitaire, has all cards reve...
The computation and memory required for kernel machines with N training samples is at least O(N2 ). Such a complexity is significant even for moderate size problems and is prohibi...
Changjiang Yang, Ramani Duraiswami, Larry S. Davis
We consider the problem of deriving class-size independent generalization bounds for some regularized discriminative multi-category classification methods. In particular, we obtai...
Given a directed graph in which some of the nodes are labeled, we investigate the question of how to exploit the link structure of the graph to infer the labels of the remaining u...