Matrix Denoising with Doubly Heteroscedastic Noise: Fundamental Limits and Optimal Spectral Methods

• URL: http://arxiv.org/abs/2405.13912v2
• Date: Mon, 28 Oct 2024 15:13:53 GMT
• Title: Matrix Denoising with Doubly Heteroscedastic Noise: Fundamental Limits and Optimal Spectral Methods
• Authors: Yihan Zhang, Marco Mondelli,
• Abstract summary: 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.
• Score: 24.06775799553418
• License:
• Abstract: 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. Existing works are either unable to pinpoint the exact asymptotic estimation error or, when they do so, the resulting approaches (e.g., based on whitening or singular value shrinkage) remain vastly suboptimal. On top of this, most of the literature has focused on the special case of estimating the left singular vector of the signal when the noise only possesses row correlation (one-sided heteroscedasticity). In contrast, our work establishes the information-theoretic and algorithmic limits of matrix denoising with doubly heteroscedastic noise. We characterize the exact asymptotic minimum mean square error, and design a novel spectral estimator with rigorous optimality guarantees: under a technical condition, it attains positive correlation with the signals whenever information-theoretically possible and, for one-sided heteroscedasticity, it also achieves the Bayes-optimal error. Numerical experiments demonstrate the significant advantage of our theoretically principled method with the state of the art. The proofs draw connections with statistical physics and approximate message passing, departing drastically from standard random matrix theory techniques.

Related papers

• Information limits and Thouless-Anderson-Palmer equations for spiked matrix models with structured noise [19.496063739638924]
  We consider a saturate problem of Bayesian inference for a structured spiked model. We show how to predict the statistical limits using an efficient algorithm inspired by the theory of adaptive Thouless-Anderson-Palmer equations.
  arXiv  Detail & Related papers  (2024-05-31T16:38:35Z)
• 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)
• Fundamental limits of Non-Linear Low-Rank Matrix Estimation [18.455890316339595]
  Bayes-optimal performances are characterized by an equivalent Gaussian model with an effective prior. We show that to reconstruct the signal accurately, one requires a signal-to-noise ratio growing as $Nfrac 12 (1-1/k_F)$, where $k_F$ is the first non-zero Fisher information coefficient of the function.
  arXiv  Detail & Related papers  (2024-03-07T05:26:52Z)
• First Order Methods with Markovian Noise: from Acceleration to Variational Inequalities [91.46841922915418]
  We present a unified approach for the theoretical analysis of first-order variation methods. Our approach covers both non-linear gradient and strongly Monte Carlo problems. We provide bounds that match the oracle strongly in the case of convex method optimization problems.
  arXiv  Detail & Related papers  (2023-05-25T11:11:31Z)
• Optimal Algorithms for the Inhomogeneous Spiked Wigner Model [89.1371983413931]
  We derive an approximate message-passing algorithm (AMP) for the inhomogeneous problem. We identify in particular the existence of a statistical-to-computational gap where known algorithms require a signal-to-noise ratio bigger than the information-theoretic threshold to perform better than random.
  arXiv  Detail & Related papers  (2023-02-13T19:57:17Z)
• Precise Asymptotics for Spectral Methods in Mixed Generalized Linear Models [31.58736590532443]
  We consider the problem of estimating two statistically independent signals in a mixed generalized linear model. Our characterization exploits a mix of tools from random matrices, free probability and the theory of approximate message passing algorithms.
  arXiv  Detail & Related papers  (2022-11-21T11:35:25Z)
• Robust Matrix Completion with Heavy-tailed Noise [0.5837881923712392]
  This paper studies low-rank matrix completion in the presence of heavy-tailed possibly asymmetric noise. In this paper, we adopt adaptive Huber loss accommodate heavy-tailed noise, which is robust against large and possibly asymmetric errors. We prove that under merely a second moment condition on the error, the Euclidean error falls geometrically fast until achieving a minimax-optimal statistical estimation error.
  arXiv  Detail & Related papers  (2022-06-09T04:48:48Z)
• Optimizing Information-theoretical Generalization Bounds via Anisotropic Noise in SGLD [73.55632827932101]
  We optimize the information-theoretical generalization bound by manipulating the noise structure in SGLD. We prove that with constraint to guarantee low empirical risk, the optimal noise covariance is the square root of the expected gradient covariance.
  arXiv  Detail & Related papers  (2021-10-26T15:02:27Z)
• High Probability Complexity Bounds for Non-Smooth Stochastic Optimization with Heavy-Tailed Noise [51.31435087414348]
  It is essential to theoretically guarantee that algorithms provide small objective residual with high probability. Existing methods for non-smooth convex optimization have complexity bounds with dependence on confidence level. We propose novel stepsize rules for two methods with gradient clipping.
  arXiv  Detail & Related papers  (2021-06-10T17:54:21Z)
• 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)
• Doubly-Stochastic Normalization of the Gaussian Kernel is Robust to Heteroskedastic Noise [3.5429774642987915]
  We show that the doubly-stochastic normalization of the Gaussian kernel with zero main diagonal is robust to heteroskedastic noise. We provide examples of simulated and experimental single-cell RNA sequence data with intrinsic heteroskedasticity.
  arXiv  Detail & Related papers  (2020-05-31T01:31:10Z)

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.