English
Related papers

Related papers: Compression Limits for Random Vectors with Linearl…

200 papers

We consider a linear model where the coefficients - intercept and slopes - are random with a law in a nonparametric class and independent from the regressors. Identification often requires the regressors to have a support which is the whole…

Statistics Theory · Mathematics 2020-06-22 Christophe Gaillac , Eric Gautier

An intriguing phenomenon in many instances of compressed sensing is that the reconstruction quality is governed not just by the overall sparsity of the signal, but also on its structure. This paper is about understanding this phenomenon,…

Functional Analysis · Mathematics 2014-03-28 Ben Adcock , Anders C. Hansen , Bogdan Roman

We consider distributed optimization problems where forming the Hessian is computationally challenging and communication is a significant bottleneck. We develop unbiased parameter averaging methods for randomized second order optimization…

Machine Learning · Statistics 2020-02-18 Burak Bartan , Mert Pilanci

The problem of estimating the covariance matrix $\Sigma$ of a $p$-variate distribution based on its $n$ observations arises in many data analysis contexts. While for $n>p$, the classical sample covariance matrix $\hat{\Sigma}_n$ is a good…

Information Theory · Computer Science 2017-09-28 Maryia Kabanava , Holger Rauhut

Asymptotic concentration behaviors of linear combinations of weight distributions on the random linear code ensemble are presented. Many important properties of a binary linear code can be expressed as the form of a linear combination of…

Information Theory · Computer Science 2008-03-10 Tadashi Wadayama

Recent research has studied the role of sparsity in high dimensional regression and signal reconstruction, establishing theoretical limits for recovering sparse models from sparse data. This line of work shows that $\ell_1$-regularized…

Machine Learning · Statistics 2012-01-11 Shuheng Zhou , John Lafferty , Larry Wasserman

We consider learning the principal subspace of a large set of vectors from an extremely small number of compressive measurements of each vector. Our theoretical results show that even a constant number of measurements per column suffices to…

Machine Learning · Statistics 2016-12-13 Akshay Krishnamurthy , Martin Azizyan , Aarti Singh

This paper presents a new method for estimating high dimensional covariance matrices. The method, permuted rank-penalized least-squares (PRLS), is based on a Kronecker product series expansion of the true covariance matrix. Assuming an…

Methodology · Statistics 2013-12-25 Theodoros Tsiligkaridis , Alfred O. Hero

We describe an image compression method, consisting of a nonlinear analysis transformation, a uniform quantizer, and a nonlinear synthesis transformation. The transforms are constructed in three successive stages of convolutional linear…

Computer Vision and Pattern Recognition · Computer Science 2020-07-28 Johannes Ballé , Valero Laparra , Eero P. Simoncelli

Hoeffding's U-statistics model combinatorial-type matrix parameters (appearing in CS theory) in a natural way. This paper proposes using these statistics for analyzing random compressed sensing matrices, in the non-asymptotic regime…

Information Theory · Computer Science 2015-06-11 Fabian Lim , Vladimir Marko Stojanovic

This article extends the concept of compressed sensing to signals that are not sparse in an orthonormal basis but rather in a redundant dictionary. It is shown that a matrix, which is a composition of a random matrix of certain type and a…

Probability · Mathematics 2010-11-10 Holger Rauhut , Karin Schnass , Pierre Vandergheynst

This paper studies fixed-rate randomized vector quantization under the constraint that the quantizer's output has a given fixed probability distribution. A general representation of randomized quantizers that includes the common models in…

Information Theory · Computer Science 2016-11-15 Naci Saldi , Tamás Linder , Serdar Yüksel

This paper investigates the theoretical problem of maintaining linear separability of the data-generating distribution under linear compression. While it has been long known that linear separability may be maintained by linear…

Machine Learning · Computer Science 2024-09-02 Paul McVay , Tie Liu , Krishna Narayanan

Boundary integral equations lead to dense system matrices when discretized, yet they are data-sparse. Using the $\mathcal{H}$-matrix format, this sparsity is exploited to achieve $\mathcal{O}(N\log N)$ complexity for storage and…

Numerical Analysis · Mathematics 2025-05-22 Kobe Bruyninckx , Daan Huybrechs , Karl Meerbergen

Higher-order tensor datasets arise commonly in recommendation systems, neuroimaging, and social networks. Here we develop probable methods for estimating a possibly high rank signal tensor from noisy observations. We consider a generative…

Methodology · Statistics 2023-04-11 Chanwoo Lee , Miaoyan Wang

Sorted data is usually easier to compress than unsorted permutations of the same data. This motivates a simple compression scheme: specify the sorted permutation of the data along with a representation of the sorted data compressed…

Data Structures and Algorithms · Computer Science 2014-11-24 Oscar Stiffelman

The present work provides an original framework for random matrix analysis based on revisiting the concentration of measure theory from a probabilistic point of view. By providing various notions of vector concentration ($q$-exponential,…

Probability · Mathematics 2021-01-19 Cosme Louart , Romain Couillet

Given a set of vectors (the data) in a Hilbert space H, we prove the existence of an optimal collection of subspaces minimizing the sum of the square of the distances between each vector and its closest subspace in the collection. This…

Classical Analysis and ODEs · Mathematics 2008-02-07 Akram Aldroubi , Carlos Cabrelli , Ursula Molter

Compressing neural nets is an active research problem, given the large size of state-of-the-art nets for tasks such as object recognition, and the computational limits imposed by mobile devices. We give a general formulation of model…

Machine Learning · Computer Science 2017-07-06 Miguel Á. Carreira-Perpiñán

Learning and compression are driven by the common aim of identifying and exploiting statistical regularities in data, which opens the door for fertile collaboration between these areas. A promising group of compression techniques for…

Machine Learning · Computer Science 2021-02-02 Fernando E. Rosas , Pedro A. M. Mediano , Michael Gastpar