Sciweavers

ALT
2010
Springer
13 years 4 months ago
PageRank Optimization in Polynomial Time by Stochastic Shortest Path Reformulation
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
Balázs Csanád Csáji, Rapha&eu...
ALT
2010
Springer
13 years 6 months ago
A Spectral Approach for Probabilistic Grammatical Inference on Trees
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...
Raphaël Bailly, Amaury Habrard, Franço...
ALT
2010
Springer
13 years 6 months ago
An Identity for Kernel Ridge Regression
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...
Fedor Zhdanov, Yuri Kalnishkan
ALT
2010
Springer
13 years 9 months ago
Recursive Teaching Dimension, Learning Complexity, and Maximum Classes
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...
Thorsten Doliwa, Hans-Ulrich Simon, Sandra Zilles
ALT
2010
Springer
13 years 9 months ago
Switching Investments
Wouter M. Koolen, Steven de Rooij
ALT
2010
Springer
13 years 11 months ago
Contrast Pattern Mining and Its Application for Building Robust Classifiers
: 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...
Kotagiri Ramamohanarao
ALT
2010
Springer
13 years 11 months ago
Distribution-Dependent PAC-Bayes Priors
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 ...
Guy Lever, François Laviolette, John Shawe-...
ALT
2010
Springer
13 years 11 months ago
Learning without Coding
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...
Samuel E. Moelius, Sandra Zilles
ALT
2010
Springer
13 years 11 months ago
A Regularization Approach to Metrical Task Systems
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...
Jacob Abernethy, Peter L. Bartlett, Niv Buchbinder...
ALT
2010
Springer
13 years 11 months ago
Lower Bounds on Learning Random Structures with Statistical Queries
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...
Dana Angluin, David Eisenstat, Leonid Kontorovich,...