Large scale canonical correlation analysis with iterative least squares
This work addresses a computational bottleneck for researchers and practitioners using CCA on large-scale data, though it appears incremental as it builds on existing fast approximation methods.
The paper tackles the problem of slow computation of Canonical Correlation Analysis (CCA) on huge datasets by introducing L-CCA, an iterative algorithm that achieves faster performance, as shown in experiments where it outperforms other fast CCA approximation schemes on two real datasets.
Canonical Correlation Analysis (CCA) is a widely used statistical tool with both well established theory and favorable performance for a wide range of machine learning problems. However, computing CCA for huge datasets can be very slow since it involves implementing QR decomposition or singular value decomposition of huge matrices. In this paper we introduce L-CCA, a iterative algorithm which can compute CCA fast on huge sparse datasets. Theory on both the asymptotic convergence and finite time accuracy of L-CCA are established. The experiments also show that L-CCA outperform other fast CCA approximation schemes on two real datasets.