TL;DR
This paper introduces Wasserstein-like metrics on Grassmannian manifolds to compare multivariate overcomplete representations, with applications in clustering and BCI dataset assessment, bridging multiple research fields.
Contribution
It proposes novel set-metrics on Grassmannian spaces for multivariate dictionaries, combining theoretical analysis and practical applications in BCI signal processing.
Findings
Metrics effectively distinguish multivariate dictionaries.
Embedded metrics improve clustering in BCI datasets.
The approach bridges Grassmannian packing, dictionary learning, and compressed sensing.
Abstract
Overcomplete representations and dictionary learning algorithms kept attracting a growing interest in the machine learning community. This paper addresses the emerging problem of comparing multivariate overcomplete representations. Despite a recurrent need to rely on a distance for learning or assessing multivariate overcomplete representations, no metrics in their underlying spaces have yet been proposed. Henceforth we propose to study overcomplete representations from the perspective of frame theory and matrix manifolds. We consider distances between multivariate dictionaries as distances between their spans which reveal to be elements of a Grassmannian manifold. We introduce Wasserstein-like set-metrics defined on Grassmannian spaces and study their properties both theoretically and numerically. Indeed a deep experimental study based on tailored synthetic datasetsand real EEG signals…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
