ALT
2010
Springer
13 years 2 months ago
2010
Springer
Abstract. The importance of a node in a directed graph can be measured by its PageRank. The PageRank of a node is used in a number of application contexts
ALT
2010
Springer
13 years 4 months ago
2010
Springer
We focus on the estimation of a probability distribution over a set of trees. We consider here the class of distributions computed by weighted automata - a strict generalization of...
ALT
2010
Springer
13 years 4 months ago
2010
Springer
This paper provides a probabilistic derivation of an identity connecting the square loss of ridge regression in on-line mode with the loss of a retrospectively best regressor. Some...
ALT
2010
Springer
13 years 7 months ago
2010
Springer
This paper is concerned with the combinatorial structure of concept classes that can be learned from a small number of examples. We show that the recently introduced notion of recu...
ALT
2010
Springer
13 years 7 months ago
2010
Springer
ALT
2010
Springer
13 years 9 months ago
2010
Springer
: The ability to distinguish, differentiate and contrast between different data sets is a key objective in data mining. Such ability can assist domain experts to understand their d...
ALT
2010
Springer
13 years 9 months ago
2010
Springer
We further develop the idea that the PAC-Bayes prior can be informed by the data-generating distribution. We prove sharp bounds for an existing framework of Gibbs algorithms, and ...
ALT
2010
Springer
13 years 9 months ago
2010
Springer
Abstract. Iterative learning is a model of language learning from positive data, due to Wiehagen. When compared to a learner in Gold's original model of language learning from...
ALT
2010
Springer
13 years 9 months ago
2010
Springer
We address the problem of constructing randomized online algorithms for the Metrical Task Systems (MTS) problem on a metric against an oblivious adversary. Restricting our attenti...
ALT
2010
Springer
13 years 9 months ago
2010
Springer
We show that random DNF formulas, random log-depth decision trees and random deterministic finite acceptors cannot be weakly learned with a polynomial number of statistical queries...