English
Related papers

Related papers: Phase transition of the Sinkhorn-Knopp algorithm

200 papers

Many real-world data sets are sparse or almost sparse. One method to measure this for a matrix $A\in \mathbb{R}^{n\times n}$ is the \emph{numerical sparsity}, denoted $\mathsf{ns}(A)$, defined as the minimum $k\geq 1$ such that…

Data Structures and Algorithms · Computer Science 2021-07-06 Vladimir Braverman , Robert Krauthgamer , Aditya Krishnan , Shay Sapir

The Frank-Wolfe algorithm has seen a resurgence in popularity due to its ability to efficiently solve constrained optimization problems in machine learning and high-dimensional statistics. As such, there is much interest in establishing…

Machine Learning · Statistics 2022-05-19 Suhas Vijaykumar

Sinkhorn algorithm has been used pervasively to approximate the solution to optimal transport (OT) and unbalanced optimal transport (UOT) problems. However, its practical application is limited due to the high computational complexity. To…

Machine Learning · Statistics 2026-04-07 Mengyu Li , Jun Yu , Tao Li , Cheng Meng

Algorithmic stability is a classical approach to understanding and analysis of the generalization error of learning algorithms. A notable weakness of most stability-based generalization bounds is that they hold only in expectation.…

Machine Learning · Computer Science 2019-06-25 Vitaly Feldman , Jan Vondrak

The Matrix-based Renyi's entropy enables us to directly measure information quantities from given data without the costly probability density estimation of underlying distributions, thus has been widely adopted in numerous statistical…

Machine Learning · Statistics 2022-05-17 Yuxin Dong , Tieliang Gong , Shujian Yu , Chen Li

We give a new framework for solving the fundamental problem of low-rank matrix completion, i.e., approximating a rank-$r$ matrix $\mathbf{M} \in \mathbb{R}^{m \times n}$ (where $m \ge n$) from random observations. First, we provide an…

Machine Learning · Computer Science 2023-08-08 Jonathan A. Kelner , Jerry Li , Allen Liu , Aaron Sidford , Kevin Tian

The subgradient method is one of the most fundamental algorithmic schemes for nonsmooth optimization. The existing complexity and convergence results for this method are mainly derived for Lipschitz continuous objective functions. In this…

Optimization and Control · Mathematics 2024-11-01 Xiao Li , Lei Zhao , Daoli Zhu , Anthony Man-Cho So

The subspace approximation problem Subspace($k$,$p$) asks for a $k$-dimensional linear subspace that fits a given set of points optimally, where the error for fitting is a generalization of the least squares fit and uses the $\ell_{p}$ norm…

Data Structures and Algorithms · Computer Science 2011-01-04 Amit Deshpande , Kasturi Varadarajan , Madhur Tulsiani , Nisheeth K. Vishnoi

The principal submatrix localization problem deals with recovering a $K\times K$ principal submatrix of elevated mean $\mu$ in a large $n\times n$ symmetric matrix subject to additive standard Gaussian noise. This problem serves as a…

Machine Learning · Statistics 2015-11-02 Bruce Hajek , Yihong Wu , Jiaming Xu

Optimal transport (OT) is a widely used tool in machine learning, but computing high-accuracy solutions for large instances remains costly. Entropic regularization and the Sinkhorn algorithm improve scalability; however, when the…

Machine Learning · Computer Science 2026-05-12 Di Wu , Ling Liang , Haizhao Yang

Generalized matrix approximation plays a fundamental role in many machine learning problems, such as CUR decomposition, kernel approximation, and matrix low rank approximation. Especially with today's applications involved in larger and…

Numerical Analysis · Computer Science 2016-09-09 Haishan Ye , Qiaoming Ye , Zhihua Zhang

Given a nonnegative matrix $A$, can you find diagonal matrices $D_1,~D_2$ such that $D_1AD_2$ is doubly stochastic? The answer to this question is known as Sinkhorn's theorem. It has been proved with a wide variety of methods, each…

Rings and Algebras · Mathematics 2016-09-22 Martin Idel

We investigate the complexity of several fundamental polynomial-time solvable problems on graphs and on matrices, when the given instance has low treewidth; in the case of matrices, we consider the treewidth of the graph formed by non-zero…

Data Structures and Algorithms · Computer Science 2015-11-05 Fedor V. Fomin , Daniel Lokshtanov , Michał Pilipczuk , Saket Saurabh , Marcin Wrochna

Natural systems often exhibit chaotic behavior in their space-time evolution. Systems transiting between chaos and order manifest a potential to compute, as shown with cellular automata and artificial neural networks. We demonstrate that…

Computational Physics · Physics 2025-04-04 Tomáš Vantuch , Ivan Zelinka , Andrew Adamatzky , Norbert Marwan

We give the first input-sparsity time algorithms for the rank-$k$ low rank approximation problem in every Schatten norm. Specifically, for a given $n\times n$ matrix $A$, our algorithm computes $Y,Z\in \mathbb{R}^{n\times k}$, which, with…

Data Structures and Algorithms · Computer Science 2020-07-01 Yi Li , David Woodruff

Recently, Musco and Woodruff (FOCS, 2017) showed that given an $n \times n$ positive semidefinite (PSD) matrix $A$, it is possible to compute a $(1+\epsilon)$-approximate relative-error low-rank approximation to $A$ by querying…

Data Structures and Algorithms · Computer Science 2021-06-16 Ainesh Bakshi , Nadiia Chepurko , David P. Woodruff

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

A fundamental problem arising in many applications in Web science and social network analysis is, given an arbitrary approximation factor $c>1$, to output a set $S$ of nodes that with high probability contains all nodes of PageRank at least…

Data Structures and Algorithms · Computer Science 2015-03-20 Christian Borgs , Michael Brautbar , Jennifer Chayes , Shang-Hua Teng

In this paper, we analyze the decision version of the NK landscape model from the perspective of threshold phenomena and phase transitions under two random distributions, the uniform probability model and the fixed ratio model. For the…

Artificial Intelligence · Computer Science 2011-06-24 J. Culberson , Y. Gao

We study a classical iterative algorithm for balancing matrices in the $L_\infty$ norm via a scaling transformation. This algorithm, which goes back to Osborne and Parlett \& Reinsch in the 1960s, is implemented as a standard preconditioner…

Data Structures and Algorithms · Computer Science 2015-06-16 Leonard J. Schulman , Alistair Sinclair
‹ Prev 1 3 4 5 6 7 10 Next ›