We consider situations where training data is abundant and computing resources are comparatively scarce. We argue that suitably designed online learning algorithms asymptotically ...
We address in this paper the question of how the knowledge of the marginal distribution P(x) can be incorporated in a learning algorithm. We suggest three theoretical methods for ...
We describe a procedure which finds a hierarchical clustering by hillclimbing. The cost function we use is a hierarchical extension of the -means cost; our local moves are tree...
We formulate linear dimensionality reduction as a semi-parametric estimation problem, enabling us to study its asymptotic behavior. We generalize the problem beyond additive Gauss...
We describe a new approximation algorithm for solving partially observable MDPs. Our bounded policy iteration approach searches through the space of bounded-size, stochastic fini...