We consider the general problem of learning from labeled and unlabeled data, which is often called semi-supervised learning or transductive inference. A principled approach to sem...
Dengyong Zhou, Olivier Bousquet, Thomas Navin Lal,...
We present an analysis of concentration-of-expectation phenomena in layered Bayesian networks that use generalized linear models as the local conditional probabilities. This frame...
Synapses are a critical element of biologically-realistic, spike-based neural computation, serving the role of communication, computation, and modification. Many different circui...
We argue that K–means and deterministic annealing algorithms for geometric clustering can be derived from the more general Information Bottleneck approach. If we cluster the ide...
We study how to learn to play a Pareto-optimal strict Nash equilibrium when there exist multiple equilibria and agents may have different preferences among the equilibria. We focu...