Canonical dependency analysis based on squared-loss mutual information

Authors:
Masayuki Karasuyama;Masashi Sugiyama
Affiliations:
Institute for Chemical Research, Kyoto University Gokasyo, Uji, Kyoto 611-0011, Japan;Tokyo Institute of Technology, 2-12-1 O-okayama, Meguro-ku, Tokyo 152-8552, Japan
Venue:
Neural Networks
Year:
2012

Citing 16
Cited 1

Fundamentals of speech recognition

Fundamentals of speech recognition
Natural gradient works efficiently in learning

Neural Computation
Kernel Canonical Correlation Analysis and Least Squares Support Vector Machines

ICANN '01 Proceedings of the International Conference on Artificial Neural Networks
On the influence of the kernel on the consistency of support vector machines

The Journal of Machine Learning Research
SINBAD: A neocortical mechanism for discovering environmental variables and regularities hidden in sensory input

Biological Cybernetics
Canonical correlation analysis based on information theory

Journal of Multivariate Analysis
Canonical Correlation Analysis: An Overview with Application to Learning Methods

Neural Computation
An introduction to ROC analysis

Pattern Recognition Letters - Special issue: ROC analysis in pattern recognition
Using KCCA for Japanese---English cross-language information retrieval and document classification

Journal of Intelligent Information Systems
Speeded-Up Robust Features (SURF)

Computer Vision and Image Understanding
Learning algorithms utilizing quasi-geodesic flows on the Stiefel manifold

Neurocomputing
A Least-squares Approach to Direct Importance Estimation

The Journal of Machine Learning Research
Canonical correlation analysis using within-class coupling

Pattern Recognition Letters
Canonical Correlation Analysis for Multilabel Classification: A Least-Squares Formulation, Extensions, and Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Measuring statistical dependence with hilbert-schmidt norms

ALT'05 Proceedings of the 16th international conference on Algorithmic Learning Theory
Application of canonical correlation analysis for identifying viral integration preferences

Bioinformatics

Freesound technical demo

Proceedings of the 21st ACM international conference on Multimedia

Quantified Score

Hi-index	0.00

Visualization

Abstract

Canonical correlation analysis (CCA) is a classical dimensionality reduction technique for two sets of variables that iteratively finds projection directions with maximum correlation. Although CCA is still in vital use in many practical application areas, recent real-world data often contain more complicated nonlinear correlations that cannot be properly captured by classical CCA. In this paper, we thus propose an extension of CCA that can effectively capture such complicated nonlinear correlations through statistical dependency maximization. The proposed method, which we call least-squares canonical dependency analysis (LSCDA), is based on a squared-loss variant of mutual information, and it has various useful properties besides its ability to capture higher-order correlations: for example, it can simultaneously find multiple projection directions (i.e., subspaces), it does not involve density estimation, and it is equipped with a model selection strategy. We demonstrate the usefulness of LSCDA through various experiments on artificial and real-world datasets.