Sciweavers

280 search results - page 24 / 56
» jmlr 2010
Sort
View
JMLR
2010
99views more  JMLR 2010»
14 years 4 months ago
Characterization, Stability and Convergence of Hierarchical Clustering Methods
We study hierarchical clustering schemes under an axiomatic view. We show that within this framework, one can prove a theorem analogous to one of J. Kleinberg (Kleinberg, 2002), i...
Gunnar Carlsson, Facundo Mémoli
JMLR
2010
119views more  JMLR 2010»
14 years 4 months ago
Semi-Supervised Learning via Generalized Maximum Entropy
Various supervised inference methods can be analyzed as convex duals of the generalized maximum entropy (MaxEnt) framework. Generalized MaxEnt aims to find a distribution that max...
Ayse Erkan, Yasemin Altun
74
Voted
JMLR
2010
115views more  JMLR 2010»
14 years 4 months ago
Bayesian structure discovery in Bayesian networks with less space
Current exact algorithms for score-based structure discovery in Bayesian networks on n nodes run in time and space within a polynomial factor of 2n . For practical use, the space ...
Pekka Parviainen, Mikko Koivisto
JMLR
2010
151views more  JMLR 2010»
14 years 4 months ago
The Feature Selection Path in Kernel Methods
The problem of automatic feature selection/weighting in kernel methods is examined. We work on a formulation that optimizes both the weights of features and the parameters of the ...
Fuxin Li, Cristian Sminchisescu
JMLR
2010
125views more  JMLR 2010»
14 years 4 months ago
Regret Bounds for Gaussian Process Bandit Problems
Bandit algorithms are concerned with trading exploration with exploitation where a number of options are available but we can only learn their quality by experimenting with them. ...
Steffen Grünewälder, Jean-Yves Audibert,...