We propose a general-purpose stochastic optimization algorithm, the so-called annealing stochastic approximation Monte Carlo (ASAMC) algorithm, for neural network training. ASAMC c...
We analyze the regret, measured in terms of log loss, of the maximum likelihood (ML) sequential prediction strategy. This "follow the leader" strategy also defines one o...
We consider an automated agent that needs to coordinate with a human partner when communication between them is not possible or is undesirable (tacit coordination games). Specifi...
Inon Zuckerman, Sarit Kraus, Jeffrey S. Rosenschei...
We relate two problems that have been explored in two distinct communities. The first is the problem of combining expert advice, studied extensively in the computational learning...
As technology for children becomes more mobile, social, and distributed, our design methods and techniques must evolve to better explore these new directions. This paper reports o...