Large-Scale Independent Vector Analysis (IVA-G) via Coresets
Loading...
Author/Creator
Date
2025
Type of Work
Department
Program
Citation of Original Publication
Gabrielson, Ben, Hanlu Yang, Trung Vu, Vince Calhoun, and Tülay Adali. "Large-Scale Independent Vector Analysis (IVA-G) via Coresets". IEEE Transactions on Signal Processing 73 (2025): 230–44. https://doi.org/10.1109/TSP.2024.3517323.
Rights
© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Subjects
UMBC Machine Learning and Signal Processing Lab (MLSP-Lab)
UMBC Ebiquity Research Group
Correlation
Analytical models
Joint blind source separation
Vectors
multiset canonical correlation analysis
Costs
Covariance matrices
Functional magnetic resonance imaging
Indexes
Numerical models
Magnetic cores
independent vector analysis
Blind source separation
UMBC Machine Learning for Signal Processing Laboratory (MLSP-Lab)
UMBC Ebiquity Research Group
Correlation
Analytical models
Joint blind source separation
Vectors
multiset canonical correlation analysis
Costs
Covariance matrices
Functional magnetic resonance imaging
Indexes
Numerical models
Magnetic cores
independent vector analysis
Blind source separation
UMBC Machine Learning for Signal Processing Laboratory (MLSP-Lab)
Abstract
Joint blind source separation (JBSS) involves the factorization of multiple matrices, i.e. “datasets”, into “sources” that are statistically dependent across datasets and independent within datasets. Despite this usefulness for analyzing multiple datasets, JBSS methods suffer from considerable computational costs and are typically intractable for hundreds or thousands of datasets. To address this issue, we present a methodology for how a subset of the datasets can be used to perform efficient JBSS over the full set. We motivate two such methods: a numerical extension of independent vector analysis (IVA) with the multivariate Gaussian model (IVA-G), and a recently proposed analytic method resembling generalized joint diagonalization (GJD). We derive nonidentifiability conditions for both methods, and then demonstrate how one can significantly improve these methods’ generalizability by an efficient representative subset selection method. This involves selecting a coreset (a weighted subset) that minimizes a measure of discrepancy between the statistics of the coreset and the full set. Using simulated and real functional magnetic resonance imaging (fMRI) data, we demonstrate significant scalability and source separation advantages of our “coreIVA-G” method vs. other JBSS methods.