English
Related papers

Related papers: Scaling positive random matrices: concentration an…

200 papers

From benign overfitting in overparameterized models to rich power-law scalings in performance, simple ridge regression displays surprising behaviors sometimes thought to be limited to deep neural networks. This balance of phenomenological…

Machine Learning · Statistics 2026-05-08 Alexander Atanasov , Jacob A. Zavatone-Veth , Cengiz Pehlevan

The self-expressive property of data points, i.e., each data point can be linearly represented by the other data points in the same subspace, has proven effective in leading subspace clustering methods. Most self-expressive methods usually…

Computer Vision and Pattern Recognition · Computer Science 2019-09-24 Jun Xu , Mengyang Yu , Ling Shao , Wangmeng Zuo , Deyu Meng , Lei Zhang , David Zhang

We study entrywise scalar quantization of two matrices prior to multiplication. Given $A\in R^{m\times k}$ and $B\in R^{k\times n}$, we quantize entries of $A$ and $B$ independently using scalar quantizers with $K_X$ and $K_Y$ levels per…

Information Theory · Computer Science 2026-03-23 Calvin Ang , Sungyoon Kim , Mert Pilanci

We present a matrix factorization algorithm that scales to input matrices that are large in both dimensions (i.e., that contains morethan 1TB of data). The algorithm streams the matrix columns while subsampling them, resulting in low…

Optimization and Control · Mathematics 2016-12-04 Arthur Mensch , Julien Mairal , Gaël Varoquaux , Bertrand Thirion

The uniform distribution on matrices with specified row and column sums is often a natural choice of null model when testing for structure in two-way tables (binary or nonnegative integer). Due to the difficulty of sampling from this…

Computation · Statistics 2013-08-14 Jeffrey W. Miller , Matthew T. Harrison

We give an algorithm that generates a uniformly random contingency table with specified marginals, i.e. a matrix with non-negative integer values and specified row and column sums. Such algorithms are useful in statistics and combinatorics.…

Combinatorics · Mathematics 2021-06-17 Andrii Arman , Pu Gao , Nicholas Wormald

We study randomly stopped sums via their asymptotic scales. First, finiteness of moments is considered. To generalise this study, asymptotic scales applicable to the class of all heavy-tailed random variables are used. The stopping is…

Probability · Mathematics 2014-05-12 Jaakko Lehtomaa

Nonnegative matrix factorization (NMF) is widely used for clustering with strong interpretability. Among general NMF problems, symmetric NMF is a special one that plays an important role in graph clustering where each element measures the…

Machine Learning · Computer Science 2023-11-07 Mengyuan Zhang , Kai Liu

We analyze the asymptotic behavior and scaling limits of large random matrices rescaled via the Sinkhorn algorithm to match prescribed row and column margins. For a random matrix with independent sub-exponential entries, we show that its…

Probability · Mathematics 2026-04-28 Danny Duan , Hanbaek Lyu , William Powell

Birkhoff polytope is the set of all bistochastic matrices (also known as doubly stochastic matrices). Bistochastic matrices form a special class of stochastic matrices where each row and column sums up to one. Permutation matrices and…

Rings and Algebras · Mathematics 2024-06-25 Suvadip Sana

In this study, we propose a projection estimation method for large-dimensional matrix factor models with cross-sectionally spiked eigenvalues. By projecting the observation matrix onto the row or column factor space, we simplify factor…

Methodology · Statistics 2020-12-04 Long Yu , Yong He , Xin-bing Kong , Xinsheng Zhang

We show several ways to round a real matrix to an integer one such that the rounding errors in all rows and columns as well as the whole matrix are less than one. This is a classical problem with applications in many fields, in particular,…

Data Structures and Algorithms · Computer Science 2007-05-23 Benjamin Doerr , Tobias Friedrich , Christian Klein , Ralf Osbild

In this work we analyze strategies for convolutional neural network scaling; that is, the process of scaling a base convolutional network to endow it with greater computational complexity and consequently representational power. Example…

Computer Vision and Pattern Recognition · Computer Science 2021-03-12 Piotr Dollár , Mannat Singh , Ross Girshick

Finding a suitable measurement matrix is an important topic in compressed sensing. Though the known random matrix, whose entries are drawn independently from a certain probability distribution, can be used as a measurement matrix and…

Information Theory · Computer Science 2013-07-09 Yi-Zheng Fan , Tao Huang , Ming Zhu

A symmetric nonnegative matrix factorization algorithm based on self-paced learning was proposed to improve the clustering performance of the model. It could make the model better distinguish normal samples from abnormal samples in an…

Machine Learning · Computer Science 2024-10-22 Lei Wang , Liang Du , Peng Zhou , Peng Wu

Random matrix theory has played an important role in various areas of pure mathematics, mathematical physics, and machine learning. From a practical perspective of data science, input data are usually normalized prior to processing. Thus,…

Machine Learning · Computer Science 2025-12-18 Hyakka Nakada , Shu Tanaka

We develop sampling algorithms to fit Bayesian hierarchical models, the computational complexity of which scales linearly with the number of observations and the number of parameters in the model. We focus on crossed random effect and…

Computation · Statistics 2025-01-03 Omiros Papaspiliopoulos , Timothée Stumpf-Fétizon , Giacomo Zanella

We study large random matrices with i.i.d. entries conditioned to have prescribed row and column sums (margins), a problem connected to relative entropy minimization, Schr\"odinger bridges, contingency tables, and random graphs with given…

Probability · Mathematics 2025-07-02 Hanbaek Lyu , Sumit Mukherjee

Scaling describes how a given quantity $Y$ that characterizes a system varies with its size $P$. For most complex systems it is of the form $Y\sim P^\beta$ with a nontrivial value of the exponent $\beta$, usually determined by regression…

Physics and Society · Physics 2019-10-16 Marc Barthelemy

Low-rank matrix approximations are often used to help scale standard machine learning algorithms to large-scale problems. Recently, matrix coherence has been used to characterize the ability to extract global information from a subset of…

Machine Learning · Statistics 2010-09-07 Mehryar Mohri , Ameet Talwalkar