Learning the parameters of an undirected graphical model is particularly difficult due to the presence of a global normalization constant. For large unstructured models computing the gradient of theâ€¦ (More)

This paper investigates the problem of finding a K-state first-order Markov chain that approximates an M -state first-order Markov chain, where K is typically much smaller than M . A variety ofâ€¦ (More)

Scoring structures of undirected graphical models by means of evaluating the marginal likelihood is very hard. The main reason is the presence of the partition function which is intractable toâ€¦ (More)

Scoring structures of undirected graphical models by means of evaluating the marginal likelihood is very hard. The main reason is the presence of the partition function which is intractable toâ€¦ (More)

We consider the problem of unsupervised learning from a matrix of data vectors where in each row the observed values are randomly permuted in an unknown fashion. Such problems arise naturally inâ€¦ (More)

We describe a probabilistic framework for learning models of pedestrian trajectories in general outdoor scenes. Possible applications include simulation of motion in computer graphics, videoâ€¦ (More)

While learning the maximum likelihood value of parameters of an undirected graphical model is hard, modelling the posterior distribution over parameters given data is harder. Yet, undirected modelsâ€¦ (More)