170 search results - page 4 / 34 » nips 2003 |
NIPS
2003
13 years 7 months ago
2003
We consider situations where training data is abundant and computing resources are comparatively scarce. We argue that suitably designed online learning algorithms asymptotically ...
NIPS
2003
13 years 7 months ago
2003
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 ...
NIPS
2003
13 years 7 months ago
2003
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...
NIPS
2003
13 years 7 months ago
2003
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...
NIPS
2003
13 years 7 months ago
2003
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...