We show that the class of strongly connected graphical models with treewidth at most k can be properly efficiently PAC-learnt with respect to the Kullback-Leibler Divergence. Prev...
This paper describes a study of agent bidding strategies, assuming combinatorial valuations for complementary and substitutable goods, in three auction environments: sequential au...
—In this paper, we investigate the maximization of the coverage time for a clustered wireless sensor network (WSN) by optimal balancing of power consumption among cluster heads (...
In this paper, we address two issues of long-standing interest in the reinforcement learning literature. First, what kinds of performance guarantees can be made for Q-learning aft...
We present algorithms for a class of resource allocation problems both in the online setting with stochastic input and in the offline setting. This class of problems contains man...
Nikhil R. Devanur, Kamal Jain, Balasubramanian Siv...