stat.MLJul 29, 2025

Stacked SVD or SVD stacked? A Random Matrix Theory perspective on data integration

Authors: Tavor Z. Baharav, Phillip B. Nicol, Rafael A. Irizarry, Rong Ma

Organizations: Eric and Wendy Schmidt Center, Broad Institute, Cambridge, MA, 02142, USA · Department of Data Science, Dana Farber Cancer Institute, Boston, MA, 02115, USA · Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, 02115, USA

Abstract

Modern data analysis increasingly requires identifying shared latent structure across multiple high-dimensional datasets. A commonly used model assumes that the data matrices are noisy observations of low-rank matrices with a shared singular subspace. In this case, two primary methods have emerged for estimating this shared structure, which vary in how they integrate information across datasets. The first approach, termed Stack-SVD, concatenates all the datasets, and then performs a singular value decomposition (SVD). The second approach, termed SVD-Stack, first performs an SVD separately for each dataset, then aggregates the top singular vectors across these datasets, and finally computes a consensus amongst them. While these methods are widely used, they have not been rigorously studied in the proportional asymptotic regime, which is of great practical relevance in today's world of increasing data size and dimensionality. Consequently, it remains unclear when one method should be preferred over another. In this work, we derive exact expressions for the asymptotic performance and phase transitions of these two methods and develop optimal weighting schemes to further improve both methods. Our analysis reveals that while neither method uniformly dominates the other in the unweighted case, optimally weighted Stack-SVD dominates optimally weighted SVD-Stack when the low rank signal is fully shared across the datasets. We then analyze multiple, partially shared components per dataset and demonstrate that SVD-Stack can yield improved performance without requiring estimation of subspace alignment. Finally, we provide practical algorithms for estimating optimal weights from data, offering theoretical guidance for method selection in practical data integration problems. Extensive numerical simulations and semi-synthetic experiments on genomic data corroborate our theoretical findings.

Explore similar work

Aug 31, 2026math.ST

Compact and Infinite-Order Error Analysis for Null-Space SVD Estimation

We study null-space estimation from a noisy matrix. For a simple left null space, we first derive an exact compact expression for the error of the smallest left singular vector. We then give an all-order series for the SVD vector and projector, followed by compact and consistently truncated series forms for the fixed-realization empirical risk and conditional population generalization risk. The recursion extends to a multiple-dimensional null space by following the complete invariant subspace. The convergence radius is not inferred from an error plot: it is computed independently from the nearest complex exceptional point that joins a retained eigenvalue branch to its complement. A reduced-nullity experiment shows that moving this spectral boundary can increase the radius, although the improvement is not monotone in the retained nullity. For individually ordered null directions under Gaussian training with τ≥mτ\geq m, we prove that the Wishart splitting matrix WW gives a strict second-order empirical ranking. Gaussian averaging equalizes the leading generalization risks at both small and very large noise, while a column-swap theorem proves strict expected generalization ranking for an isotropic signal subspace. For unequal spikes, an exact population-overlap criterion and a simultaneous 99%99\% Monte Carlo confidence certificate explain the observed intermediate ranking. A sixth-order risk correction improves the lower-crossover estimate in the reported experiment. This equal--ranked--equal phenomenon is a finite-sample diagnostic related to spectral mixing, but its tolerance crossings, the exceptional-point radius, and the asymptotic BBP threshold are three distinct quantities.
Xin Li, Jonathan Cohen, Rami Puzis
May 27, 2026math.OC

Manifold-based Algorithms for the Hadamard Decomposition

Given a matrix XX, and two ranks r1r_1 and r2r_2, the Hadamard decomposition (HD) looks for two low-rank matrices, X1X_1 of rank r1r_1 and X2X_2 of rank r2r_2, both of the same size as XX, such that X≈X1∘X2X\approx X_1\circ X_2, where ∘\circ is the Hadamard (element-wise) product. In most cases, HD is more expressive than standard low-rank approximations such as the truncated singular value decomposition (TSVD), as it can represent higher-rank matrices with the same number of parameters; this is because the rank of X1∘X2X_1 \circ X_2 is generically equal to r1r2r_1 r_2. In this paper, we first present some theoretical insights for HD, in particular a useful reformulation X≈WH⊤X\approx WH^\top where WW and HH have r1r2r_1 r_2 columns and belong to certain manifolds. These allow us to develop three new algorithms for computing HD. The first one uses the representation X≈X1∘X2X\approx X_1\circ X_2 and relies on the Manopt toolbox. The other two rely on the reformulation X≈WH⊤X\approx WH^\top: one is a block projected gradient method, and the other is a manifold-based gradient descent algorithm that does not require projection onto the feasible set. The last two algorithms are particularly effective for handling large sparse data. We also propose new initializations that allow us to improve the accuracy of the HD. We compare our algorithms and initialization strategies with the TSVD and with the state of the art. Numerical results show that the new methods are efficient and competitive on both synthetic and real data.
Nicolas Gillis, Subhayan Saha, Stefano Sicilia +1
Sep 16, 2026cs.LG

Randomized SVD Approximations for Spectral Co-Clustering of Word-Document Matrices

Spectral co-clustering is a useful tool for discovering latent structure in word-document matrices, but its reliance on singular value decomposition (SVD) can make standard formulations expensive on high-dimensional data. This paper presents two randomized approximations for normalized spectral co-clustering of bipartite text data when the numbers of document and word clusters may differ. The first method uses randomized SVD through random projection, while the second combines partial SVD with element-wise random sampling. Across real-world and synthetic datasets, both methods reduce runtime relative to the full-SVD baseline, but their behavior depends on matrix sparsity. The random projection method is the more reliable approximation across the tested settings, whereas the sampling-based method is most useful on denser matrices and provides limited benefit on already sparse text data. These results show that randomized approximations for spectral co-clustering should be selected according to the underlying structure of the data.
Fateme Mazdarani, Carlos Toxtli