Local Canonical Correlation Analysis for Nonlinear Common Variables Discovery

Abstract

In this paper, we address the problem of hidden common variables discovery from multimodal data sets of nonlinear high-dimensional observations. We present a metric based on local applications of canonical correlation analysis (CCA) and incorporate it in a kernel-based manifold learning technique.We show that this metric discovers the hidden common variables underlying the multimodal observations by estimating the Euclidean distance between them. Our approach can be viewed both as an extension of CCA to a nonlinear setting as well as an extension of manifold learning to multiple data sets. Experimental results show that our method indeed discovers the common variables underlying high-dimensional nonlinear observations without assuming prior rigid model assumptions.

References in corpus (3)

• Nonparametric Canonical Correlation Analysis
• Canonical Correlation Forests
• Data-Driven Reduction for Multiscale Stochastic Dynamical Systems

Cited by in corpus (4)

• Spectral Discovery of Jointly Smooth Features for Multimodal Data
• Diffusion-based nonlinear filtering for multimodal data fusion with application to sleep stage assessment
• Multimodal Latent Variable Analysis
• Connecting Dots -- from Local Covariance to Empirical Intrinsic Geometry and Locally Linear Embedding