ICML
2007
IEEE
15 years 1 months ago
2007
IEEE
We study the problem of simultaneously estimating several densities where the datasets are organized into overlapping groups, such as a hierarchy. For this problem, we propose a m...
ICML
2007
IEEE
15 years 1 months ago
2007
IEEE
In supervised learning, we commonly assume that training and test data are sampled from the same distribution. However, this assumption can be violated in practice and then standa...
ICML
2007
IEEE
15 years 1 months ago
2007
IEEE
We introduce a new inference algorithm for Dirichlet process mixture models. While Gibbs sampling and variational methods focus on local moves, the new algorithm makes more global...
ICML
2007
IEEE
15 years 1 months ago
2007
IEEE
ICML
2007
IEEE
15 years 1 months ago
2007
IEEE
We propose statistical predicate invention as a key problem for statistical relational learning. SPI is the problem of discovering new concepts, properties and relations in struct...
ICML
2007
IEEE
15 years 1 months ago
2007
IEEE
Given observed data and a collection of parameterized candidate models, a 1- confidence region in parameter space provides useful insight as to those models which are a good fit t...
ICML
2007
IEEE
15 years 1 months ago
2007
IEEE
We propose a family of clustering algorithms based on the maximization of dependence between the input variables and their cluster labels, as expressed by the Hilbert-Schmidt Inde...
ICML
2007
IEEE
15 years 1 months ago
2007
IEEE
Recently, several learning algorithms relying on models with deep architectures have been proposed. Though they have demonstrated impressive performance, to date, they have only b...
ICML
2007
IEEE
15 years 1 months ago
2007
IEEE
Large-scale logistic regression arises in many applications such as document classification and natural language processing. In this paper, we apply a trust region Newton method t...
ICML
2007
IEEE
15 years 1 months ago
2007
IEEE
We describe and analyze a simple and effective iterative algorithm for solving the optimization problem cast by Support Vector Machines (SVM). Our method alternates between stocha...