The paper introduces Sparse Separable Factor Analysis (SSFA), a latent factor model designed for complex-valued arrays that preserves amplitude and phase information. SSFA models each mode’s covariance with a low‑rank Hermitian factor structure plus a diagonal residual, applying element‑wise lasso penalties to achieve interpretable, phase‑preserving loadings via complex soft‑thresholding. The method is validated through simulations showing improved covariance estimation over vectorization approaches and applied to local field potential data from mice to compare separability across brain region, frequency, and time, as well as to impute missing recordings due to electrode misplacement.
arXiv:2304.06522v3 Announce Type: replace-cross Abstract: Signal extraction is difficult when the number of variables $N$ is much larger than the number of observations $M$. We address this problem u...
arXiv:2607. 27507v1 Announce Type: new Abstract: Matrix factorisation is a fundamental tool for exploiting low-dimensional structure in high-dimensional data, with applications such as data compression, denoising, structure discovery, interpretable representation learning, and dimensionality reduction.
arXiv:1811. 05336v2 Announce Type: replace-cross Abstract: Inference for factor models is often hampered by the lack of tractable and accurate variance estimates, which can materially distort downstream analyses.
arXiv:2412. 07041v4 Announce Type: replace-cross Abstract: Recovering incomplete multidimensional tensor-structured data is a fundamental task in many real-world applications.
arXiv:2610.28330v1 Announce Type: cross Abstract: We study a linear mixing model with dependent latent components, assuming multiple data domains. Most existing models assume that the components are...
arXiv:2606.08560v2 Announce Type: replace-cross Abstract: We adopt the canonical polyadic (CP) decomposition to model high-dimensional tensor time series. Our primary goal is to identify and estimate...
arXiv:2601. 18128v2 Announce Type: replace-cross Abstract: High-dimensional data often exhibit variation that can be captured by lower-dimensional factors.
arXiv:2607. 22262v1 Announce Type: cross Abstract: Modeling shared and subject-specific structure in multisubject spatiotemporal data remains challenging, particularly in neuroimaging, where both spatial and temporal patterns exhibit rich variability across subjects.
arXiv:2610.06930v1 Announce Type: cross Abstract: Multivariate functional data arise in many modern manufacturing systems, where multiple sensors record densely sampled process trajectories. Monitori...
arXiv:2608. 13234v1 Announce Type: new Abstract: In order to understand complex systems such as the human metabolome or human brain, different sensing technologies are used, generating complex data.
arXiv:2609.14815v1 Announce Type: cross Abstract: This paper introduces a novel framework for Regularized Multivariate Functional Principal Component Analysis (ReMFPCA) via Functional Singular Value...
arXiv:2610.07284v1 Announce Type: cross Abstract: Spectral methods are central to high-dimensional statistics and machine learning, underlying procedures for covariance estimation, matrix denoising,...