English
Related papers

Related papers: Optimal Shrinkage of Singular Values

200 papers

Unlike the ordinary least-squares (OLS) estimator for the linear model, a ridge regression linear model provides coefficient estimates via shrinkage, usually with improved mean-square and prediction error. This is true especially when the…

Methodology · Statistics 2015-06-25 George Karabatsos

In this paper, we theoretically investigate the low-rank matrix recovery problem in the context of the unconstrained regularized nuclear norm minimization (RNNM) framework. Our theoretical findings show that, the RNNM method is able to…

Numerical Analysis · Mathematics 2021-03-09 Wendong Wang , Feng Zhang , Jianjun Wang

Weight decay is ubiquitous in training deep neural network architectures. Its empirical success is often attributed to capacity control; nonetheless, our theoretical understanding of its effect on the loss landscape and the set of…

Machine Learning · Statistics 2026-03-31 Anil Kamber , Rahul Parhi

We introduce a new criterion, the Rank Selection Criterion (RSC), for selecting the optimal reduced rank estimator of the coefficient matrix in multivariate response regression models. The corresponding RSC estimator minimizes the Frobenius…

Statistics Theory · Mathematics 2011-10-18 Florentina Bunea , Yiyuan She , Marten H. Wegkamp

We analyze the landscape and training dynamics of diagonal linear networks in a linear regression task, with the network parameters being perturbed by small isotropic normal noise. The addition of such noise may be interpreted as a…

Machine Learning · Computer Science 2025-03-18 Gabriel Clara , Sophie Langer , Johannes Schmidt-Hieber

Recent work has generalized several results concerning the well-understood spiked Wigner matrix model of a low-rank signal matrix corrupted by additive i.i.d. Gaussian noise to the inhomogeneous case, where the noise has a variance profile.…

Statistics Theory · Mathematics 2025-10-10 Debsurya De , Dmitriy Kunisky

Estimating the frequencies of multiple sinusoids in the presence of AWGN and when the data record is short is commonly accomplished by subspace-based methods such as ESPRIT, MUSIC, Min-Norm, etc. These methods do not assume that the data…

Signal Processing · Electrical Eng. & Systems 2020-08-31 P. Vishnu , C. S. Ramalingam

We propose an approximation method for thresholding of singular values using Chebyshev polynomial approximation (CPA). Many signal processing problems require iterative application of singular value decomposition (SVD) for minimizing the…

Numerical Analysis · Computer Science 2017-11-22 Masaki Onuki , Shunsuke Ono , Keiichiro Shirai , Yuichi Tanaka

In this paper, we investigate the theoretical guarantees of penalized $\lun$ minimization (also called Basis Pursuit Denoising or Lasso) in terms of sparsity pattern recovery (support and sign consistency) from noisy measurements with…

Information Theory · Computer Science 2011-09-13 Charles Dossal , Marie-Line Chabanol , Gabriel Peyré , Jalal Fadili

We study the completion of approximately low rank matrices with entries missing not at random (MNAR). In the context of typical large-dimensional statistical settings, we establish a framework for the performance analysis of the nuclear…

Information Theory · Computer Science 2024-01-02 Agostino Capponi , Mihailo Stojnic

Tensor completion is a fundamental tool for incomplete data analysis, where the goal is to predict missing entries from partial observations. However, existing methods often make the explicit or implicit assumption that the observed entries…

Machine Learning · Statistics 2022-03-18 Yuning Qiu , Guoxu Zhou , Qibin Zhao , Shengli Xie

In this paper, we consider a compressed sensing problem of reconstructing a sparse signal from an undersampled set of noisy linear measurements. The regularized least squares or least absolute shrinkage and selection operator (LASSO)…

Information Theory · Computer Science 2014-10-30 Chao-Kai Wen , Jun Zhang , Kai-Kit Wong , Jung-Chieh Chen , Chau Yuen

Much of the existing literature in sparse recovery is concerned with the following question: given a sparsity pattern and a corresponding regularizer, derive conditions on the dictionary under which exact recovery is possible. In this…

Signal Processing · Electrical Eng. & Systems 2020-07-24 Mustafa D. Kaba , Mengnan Zhao , Rene Vidal , Daniel P. Robinson , Enrique Mallada

We address the problem of recovering a sparse signal from clipped or quantized measurements. We show how these two problems can be formulated as minimizing the distance to a convex feasibility set, which provides a convex and differentiable…

Signal Processing · Electrical Eng. & Systems 2018-12-05 Lucas Rencker , Francis Bach , Wenwu Wang , Mark D. Plumbley

We proposed a weighted l1 minimization to recover a sparse signal vector and the corrupted noise vector from a linear measurement when the sensing matrix A is an m by n row i.i.d subgaussian matrix. We obtain both uniform and nonuniform…

Information Theory · Computer Science 2016-01-25 Dongcai Su

A new wave of work on covariance cleaning and nonlinear shrinkage has delivered asymptotically optimal analytical solutions for large covariance matrices. The same framework has been generalized to empirical cross-covariance matrices, whose…

Statistical Finance · Quantitative Finance 2026-01-22 Efstratios Manolakis , Christian Bongiorno , Rosario Nunzio Mantegna

We propose two novel approaches to the recovery of an (approximately) sparse signal from noisy linear measurements in the case that the signal is a priori known to be non-negative and obey given linear equality constraints, such as simplex…

Information Theory · Computer Science 2015-06-17 Jeremy Vila , Philip Schniter

The performance of estimating the common support for jointly sparse signals based on their projections onto lower-dimensional space is analyzed. Support recovery is formulated as a multiple-hypothesis testing problem. Both upper and lower…

Information Theory · Computer Science 2009-11-05 Gongguo Tang , Arye Nehorai

We study estimation of the covariance matrix under relative condition number loss $\kappa(\Sigma^{-1/2} \hat{\Sigma} \Sigma^{-1/2})$, where $\kappa(\Delta)$ is the condition number of matrix $\Delta$, and $\hat{\Sigma}$ and $\Sigma$ are the…

Statistics Theory · Mathematics 2018-10-18 David L. Donoho , Behrooz Ghorbani

We develop a class of minimax estimators for a normal mean matrix under the Frobenius loss, which generalizes the James--Stein and Efron--Morris estimators. It shrinks the Schatten norm towards zero and works well for low-rank matrices. We…

Statistics Theory · Mathematics 2024-06-11 Xiao Li , Takeru Matsuda , Fumiyasu Komaki
‹ Prev 1 8 9 10 Next ›