English
Related papers

Related papers: Information-Theoretic Limits for the Matrix Tensor…

200 papers

We study the recovery of multiple high-dimensional signals from two noisy, correlated modalities: a spiked matrix and a spiked tensor sharing a common low-rank structure. This setting generalizes classical spiked matrix and tensor models,…

Machine Learning · Statistics 2025-06-04 Hugo Tabanelli , Pierre Mergny , Lenka Zdeborova , Florent Krzakala

We study the tradeoff between the statistical error and communication cost of distributed statistical estimation problems in high dimensions. In the distributed sparse Gaussian mean estimation problem, each of the $m$ machines receives $n$…

Machine Learning · Computer Science 2016-05-11 Mark Braverman , Ankit Garg , Tengyu Ma , Huy L. Nguyen , David P. Woodruff

In recent years, promising statistical modeling approaches to tensor data analysis have been rapidly developed. Traditional multivariate analysis tools, such as multivariate regression and discriminant analysis, are generalized from…

Methodology · Statistics 2023-06-22 Ning Wang , Xin Zhang , Qing Mai

Sparse coding--that is, modelling data vectors as sparse linear combinations of basis elements--is widely used in machine learning, neuroscience, signal processing, and statistics. This paper focuses on the large-scale matrix factorization…

Machine Learning · Statistics 2010-02-11 Julien Mairal , Francis Bach , Jean Ponce , Guillermo Sapiro

We consider tensor factorizations based on sparse measurements of the components of relatively high rank tensors. The measurements are designed in a way that the underlying graph of interactions is a random graph. The setup will be useful…

Machine Learning · Statistics 2026-04-15 Angelo Giorgio Cavaliere , Riki Nagasawa , Shuta Yokoi , Tomoyuki Obuchi , Hajime Yoshino

We propose a new method for low-rank approximation of Moore-Penrose pseudoinverses (MPPs) of large-scale matrices using tensor networks. The computed pseudoinverses can be useful for solving or preconditioning of large-scale overdetermined…

Numerical Analysis · Mathematics 2016-07-06 Namgil Lee , Andrzej Cichocki

Information divergence that measures the difference between two nonnegative matrices or tensors has found its use in a variety of machine learning problems. Examples are Nonnegative Matrix/Tensor Factorization, Stochastic Neighbor…

Machine Learning · Computer Science 2014-06-06 Onur Dikmen , Zhirong Yang , Erkki Oja

The discrete empirical interpolation method (DEIM) is a well-established approach, widely used for state reconstruction using sparse sensor/measurement data, nonlinear model reduction, and interpretable feature selection. We introduce the…

Numerical Analysis · Mathematics 2024-10-21 Sridhar Chellappa , Lihong Feng , Peter Benner

We consider increasingly complex models of matrix denoising and dictionary learning in the Bayes-optimal setting, in the challenging regime where the matrices to infer have a rank growing linearly with the system size. This is in contrast…

Information Theory · Computer Science 2022-09-14 Jean Barbier , Nicolas Macris

We analyse the matrix factorization problem. Given a noisy measurement of a product of two matrices, the problem is to estimate back the original matrices. It arises in many applications such as dictionary learning, blind matrix…

Numerical Analysis · Computer Science 2016-07-19 Yoshiyuki Kabashima , Florent Krzakala , Marc Mézard , Ayaka Sakata , Lenka Zdeborová

Communication lower bounds have long been established for matrix multiplication algorithms. However, most methods of asymptotic analysis have either ignored the constant factors or not obtained the tightest possible values. Recent work has…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-05-27 Hussam Al Daas , Grey Ballard , Laura Grigori , Suraj Kumar , Kathryn Rouse

We develop both first and second order numerical optimization methods to solve non-smooth optimization problems featuring a shared sparsity penalty, constrained by differential equations with uncertainty. To alleviate the curse of…

Optimization and Control · Mathematics 2025-09-18 Harbir Antil , Sergey Dolgov , Akwum Onwunta

There has been definite progress recently in proving the variational single-letter formula given by the heuristic replica method for various estimation problems. In particular, the replica formula for the mutual information in the case of…

Information Theory · Computer Science 2018-11-16 Jean Barbier , Nicolas Macris , Antoine Maillard , Florent Krzakala

We examine a class of deep learning models with a tractable method to compute information-theoretic quantities. Our contributions are three-fold: (i) We show how entropies and mutual informations can be derived from heuristic statistical…

Machine Learning · Computer Science 2020-01-22 Marylou Gabrié , Andre Manoel , Clément Luneau , Jean Barbier , Nicolas Macris , Florent Krzakala , Lenka Zdeborová

By a tensor we mean an element of a tensor product of vector spaces over a field. Up to a choice of bases in factors of tensor products, every tensor may be coordinatized, that is, represented as an array consisting of numbers. This note is…

Functional Analysis · Mathematics 2019-01-11 R. N. Gumerov , A. S. Sharafutdinov

The objective of this paper is to investigate a new numerical method for the approximation of the self-diffusion matrix of a tagged particle process defined on a grid. While standard numerical methods make use of long-time averages of…

Numerical Analysis · Mathematics 2023-02-27 Jad Dabaghi , Virginie Ehrlacher , Christoph Strössner

We investigate the theoretical foundations of a recently introduced entropy-based formulation of weighted least squares for the approximation of overdetermined linear systems, motivated by robust data fitting in the presence of sparse gross…

Numerical Analysis · Mathematics 2026-03-17 Felice Iavernaro , Monica Lazzo , Lorenzo Pisani

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,…

Statistics Theory · Mathematics 2024-10-29 Yihan Zhang , Marco Mondelli

We consider a statistical model for finite-rank symmetric tensor factorization and prove a single-letter variational expression for its asymptotic mutual information when the tensor is of even order. The proof applies the adaptive…

Information Theory · Computer Science 2020-09-24 Clément Luneau , Jean Barbier , Nicolas Macris

We introduce the Mutual Information Machine (MIM), a novel formulation of representation learning, using a joint distribution over the observations and latent state in an encoder/decoder framework. Our key principles are symmetry and mutual…

Machine Learning · Statistics 2019-10-10 Micha Livne , Kevin Swersky , David J. Fleet