Adaptive Canonical Correlation Analysis Based On Matrix Manifolds

Abstract

In this paper, we formulate the Canonical Correlation Analysis (CCA) problem on matrix manifolds. This framework provides a natural way for dealing with matrix constraints and tools for building efficient algorithms even in an adaptive setting. Finally, an adaptive CCA algorithm is proposed and applied to a change detection problem in EEG signals.

Appears in Proceedings of the 29th International Conference on Machine Learning (ICML 2012)

References in corpus (1)

• A kernel method for canonical correlation analysis

Cited by in corpus (6)

• Large-Scale Approximate Kernel Canonical Correlation Analysis
• Stochastic Optimization for Deep CCA via Nonlinear Orthogonal Iterations
• Quadratic Optimization with Orthogonality Constraints: Explicit Lojasiewicz Exponent and Linear Convergence of Line-Search Methods
• Efficient Globally Convergent Stochastic Optimization for Canonical Correlation Analysis
• Faster Randomized Methods for Orthogonality Constrained Problems
• Tensor Canonical Correlation Analysis with Convergence and Statistical Guarantees