Extreme value theory for singular subspace estimation in the matrix denoising model

• URL: http://arxiv.org/abs/2507.19978v1
• Date: Sat, 26 Jul 2025 15:28:36 GMT
• Title: Extreme value theory for singular subspace estimation in the matrix denoising model
• Authors: Junhyung Chang, Joshua Cape,
• Abstract summary: We study fine-grained singular subspace estimation in the matrix denoising model.<n>We apply our distributional theory to test hypotheses of low-rank signal structure encoded in the leading singular vectors.
• Score: 0.4297070083645049
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper studies fine-grained singular subspace estimation in the matrix denoising model where a deterministic low-rank signal matrix is additively perturbed by a stochastic matrix of Gaussian noise. We establish that the maximum Euclidean row norm (i.e., the two-to-infinity norm) of the aligned difference between the leading sample and population singular vectors approaches the Gumbel distribution in the large-matrix limit, under suitable signal-to-noise conditions and after appropriate centering and scaling. We apply our novel asymptotic distributional theory to test hypotheses of low-rank signal structure encoded in the leading singular vectors and their corresponding principal subspace. We provide de-biased estimators for the corresponding nuisance signal singular values and show that our proposed plug-in test statistic has desirable properties. Notably, compared to using the Frobenius norm subspace distance, our test statistic based on the two-to-infinity norm has higher power to detect structured alternatives that differ from the null in only a few matrix entries or rows. Our main results are obtained by a novel synthesis of and technical analysis involving entrywise matrix perturbation analysis, extreme value theory, saddle point approximation methods, and random matrix theory. Our contributions complement the existing literature for matrix denoising focused on minimaxity, mean squared error analysis, unitarily invariant distances between subspaces, component-wise asymptotic distributional theory, and row-wise uniform error bounds. Numerical simulations illustrate our main results and demonstrate the robustness properties of our testing procedure to non-Gaussian noise distributions.

Related papers

• Absorb and Converge: Provable Convergence Guarantee for Absorbing Discrete Diffusion Models [59.47572583027685]
  We provide the first finite-time error bounds and convergence rate analysis for discrete diffusion models using absorbing rate matrices.<n>We establish the first convergence guarantees for both the $tau$-leaping and uniformization samplers under absorbing rate matrices.<n>Under suitable assumptions, we provide convergence guarantees without early stopping.
  arXiv  Detail & Related papers  (2025-06-02T23:14:35Z)
• Statistical Limits in Random Tensors with Multiple Correlated Spikes [6.614637831308917]
  We use tools from random matrix theory to study the multi-spiked tensor model.<n>We study the phase transition phenomenon for finding critical points of the corresponding optimization problem.<n>We propose a new estimator of the rank-$r$ weights by solving a system of equations.
  arXiv  Detail & Related papers  (2025-03-05T10:37:54Z)
• Entrywise error bounds for low-rank approximations of kernel matrices [55.524284152242096]
  We derive entrywise error bounds for low-rank approximations of kernel matrices obtained using the truncated eigen-decomposition. A key technical innovation is a delocalisation result for the eigenvectors of the kernel matrix corresponding to small eigenvalues. We validate our theory with an empirical study of a collection of synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2024-05-23T12:26:25Z)
• Matrix Denoising with Doubly Heteroscedastic Noise: Fundamental Limits and Optimal Spectral Methods [24.06775799553418]
  We study the matrix denoising problem of estimating the singular vectors of a rank-$1$ signal corrupted by noise with both column and row correlations. Our work establishes the information-theoretic and algorithmic limits of matrix denoising with doubly heteroscedastic noise.
  arXiv  Detail & Related papers  (2024-05-22T18:38:10Z)
• A general error analysis for randomized low-rank approximation with application to data assimilation [42.57210316104905]
  We propose a framework for the analysis of the low-rank approximation error in Frobenius norm for centered and non-standard matrices. Under minimal assumptions, we derive accurate bounds in expectation and probability. Our bounds have clear interpretations that enable us to derive properties and motivate practical choices.
  arXiv  Detail & Related papers  (2024-05-08T04:51:56Z)
• Leave-one-out Singular Subspace Perturbation Analysis for Spectral Clustering [7.342677574855651]
  The singular subspaces perturbation theory is of fundamental importance in probability and statistics. We consider two arbitrary matrices where one is a leave-one-column-out submatrix of the other one. It is well-suited for mixture models and results in a sharper and finer statistical analysis than classical perturbation bounds such as Wedin's Theorem.
  arXiv  Detail & Related papers  (2022-05-30T05:07:09Z)
• Semi-Supervised Subspace Clustering via Tensor Low-Rank Representation [64.49871502193477]
  We propose a novel semi-supervised subspace clustering method, which is able to simultaneously augment the initial supervisory information and construct a discriminative affinity matrix. Comprehensive experimental results on six commonly-used benchmark datasets demonstrate the superiority of our method over state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-05-21T01:47:17Z)
• Optimal policy evaluation using kernel-based temporal difference methods [78.83926562536791]
  We use kernel Hilbert spaces for estimating the value function of an infinite-horizon discounted Markov reward process. We derive a non-asymptotic upper bound on the error with explicit dependence on the eigenvalues of the associated kernel operator. We prove minimax lower bounds over sub-classes of MRPs.
  arXiv  Detail & Related papers  (2021-09-24T14:48:20Z)
• Minimax Estimation of Linear Functions of Eigenvectors in the Face of Small Eigen-Gaps [95.62172085878132]
  Eigenvector perturbation analysis plays a vital role in various statistical data science applications. We develop a suite of statistical theory that characterizes the perturbation of arbitrary linear functions of an unknown eigenvector. In order to mitigate a non-negligible bias issue inherent to the natural "plug-in" estimator, we develop de-biased estimators.
  arXiv  Detail & Related papers  (2021-04-07T17:55:10Z)
• Understanding Implicit Regularization in Over-Parameterized Single Index Model [55.41685740015095]
  We design regularization-free algorithms for the high-dimensional single index model. We provide theoretical guarantees for the induced implicit regularization phenomenon.
  arXiv  Detail & Related papers  (2020-07-16T13:27:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.