Sciweavers

ICML
2009
IEEE
14 years 4 months ago
Detecting the direction of causal time series
We propose a method that detects the true direction of time series, by fitting an autoregressive moving average model to the data. Whenever the noise is independent of the previou...
Arthur Gretton, Bernhard Schölkopf, Dominik J...
ICML
2009
IEEE
14 years 4 months ago
Multi-assignment clustering for Boolean data
Conventional clustering methods typically assume that each data item belongs to a single cluster. This assumption does not hold in general. In order to overcome this limitation, w...
Andreas P. Streich, Mario Frank, David A. Basin, J...
ICML
2009
IEEE
14 years 4 months ago
Bayesian clustering for email campaign detection
We discuss the problem of clustering elements according to the sources that have generated them. For elements that are characterized by independent binary attributes, a closedform...
Peter Haider, Tobias Scheffer
ICML
2009
IEEE
14 years 4 months ago
Efficient Euclidean projections in linear time
We consider the problem of computing the Euclidean projection of a vector of length n onto a closed convex set including the 1 ball and the specialized polyhedra employed in (Shal...
Jun Liu, Jieping Ye
ICML
2009
IEEE
14 years 4 months ago
Analytic moment-based Gaussian process filtering
We propose an analytic moment-based filter for nonlinear stochastic dynamic systems modeled by Gaussian processes. Exact expressions for the expected value and the covariance matr...
Marc Peter Deisenroth, Marco F. Huber, Uwe D. Hane...
ICML
2009
IEEE
14 years 4 months ago
Partially supervised feature selection with regularized linear models
This paper addresses feature selection techniques for classification of high dimensional data, such as those produced by microarray experiments. Some prior knowledge may be availa...
Thibault Helleputte, Pierre Dupont
ICML
2009
IEEE
14 years 4 months ago
Learning non-redundant codebooks for classifying complex objects
Codebook-based representations are widely employed in the classification of complex objects such as images and documents. Most previous codebook-based methods construct a single c...
Wei Zhang, Akshat Surve, Xiaoli Fern, Thomas G. Di...
ICML
2009
IEEE
14 years 4 months ago
Factored conditional restricted Boltzmann Machines for modeling motion style
The Conditional Restricted Boltzmann Machine (CRBM) is a recently proposed model for time series that has a rich, distributed hidden state and permits simple, exact inference. We ...
Graham W. Taylor, Geoffrey E. Hinton
ICML
2009
IEEE
14 years 4 months ago
A simpler unified analysis of budget perceptrons
The kernel Perceptron is an appealing online learning algorithm that has a drawback: whenever it makes an error it must increase its support set, which slows training and testing ...
Ilya Sutskever