English
Related papers

Related papers: Sublinear Time Low-Rank Approximation of Hankel Ma…

200 papers

Low-rank approximation and column subset selection are two fundamental and related problems that are applied across a wealth of machine learning applications. In this paper, we study the question of socially fair low-rank approximation and…

Machine Learning · Computer Science 2024-12-10 Zhao Song , Ali Vakilian , David P. Woodruff , Samson Zhou

We consider relative error low rank approximation of $tensors$ with respect to the Frobenius norm: given an order-$q$ tensor $A \in \mathbb{R}^{\prod_{i=1}^q n_i}$, output a rank-$k$ tensor $B$ for which $\|A-B\|_F^2 \leq (1+\epsilon)$OPT,…

Data Structures and Algorithms · Computer Science 2018-04-02 Zhao Song , David P. Woodruff , Peilin Zhong

This paper studies the problem of finding an $(1+\epsilon)$-approximate solution to positive semidefinite programs. These are semidefinite programs in which all matrices in the constraints and objective are positive semidefinite and all…

Data Structures and Algorithms · Computer Science 2016-02-23 Richard Peng , Kanat Tangwongsan , Peng Zhang

We are interested in computing $k$ most preferred models of a given d-DNNF circuit $C$, where the preference relation is based on an algebraic structure called a monotone, totally ordered, semigroup $(K, \otimes, <)$. In our setting, every…

Artificial Intelligence · Computer Science 2022-05-09 Pierre Bourhis , Laurence Duchien , Jérémie Dusart , Emmanuel Lonca , Pierre Marquis , Clément Quinton

We prove a \emph{query complexity} lower bound on rank-one principal component analysis (PCA). We consider an oracle model where, given a symmetric matrix $M \in \mathbb{R}^{d \times d}$, an algorithm is allowed to make $T$ \emph{exact}…

Machine Learning · Computer Science 2017-04-18 Max Simchowitz , Ahmed El Alaoui , Benjamin Recht

We study the problem of testing whether a matrix $\mathbf{A} \in \mathbb{R}^{n \times n}$ with bounded entries ($\|\mathbf{A}\|_\infty \leq 1$) is positive semi-definite (PSD), or $\epsilon$-far in Euclidean distance from the PSD cone,…

Data Structures and Algorithms · Computer Science 2020-09-21 Ainesh Bakshi , Nadiia Chepurko , Rajesh Jayaram

We study the complexity of approximate representation and learning of submodular functions over the uniform distribution on the Boolean hypercube $\{0,1\}^n$. Our main result is the following structural theorem: any submodular function is…

Machine Learning · Computer Science 2013-04-03 Vitaly Feldman , Pravesh Kothari , Jan Vondrak

Positive semidefinite programs are an important subclass of semidefinite programs in which all matrices involved in the specification of the problem are positive semidefinite and all scalars involved are non-negative. We present a parallel…

Computational Complexity · Computer Science 2011-04-14 Rahul Jain , Penghui Yao

This paper studies the problem of identifying low-order linear systems via Hankel nuclear norm regularization. Hankel regularization encourages the low-rankness of the Hankel matrix, which maps to the low-orderness of the system. We provide…

Machine Learning · Statistics 2022-04-01 Yue Sun , Samet Oymak , Maryam Fazel

We study Helson matrices (also known as multiplicative Hankel matrices), i.e. infinite matrices of the form $M(\alpha) = \{\alpha(nm)\}_{n,m=1}^\infty$, where $\alpha$ is a sequence of complex numbers. Helson matrices are considered as…

Functional Analysis · Mathematics 2017-08-31 Karl-Mikael Perfekt , Alexander Pushnitski

Composite convex optimization problems which include both a nonsmooth term and a low-rank promoting term have important applications in machine learning and signal processing, such as when one wishes to recover an unknown matrix that is…

Machine Learning · Computer Science 2018-09-28 Dan Garber , Atara Kaplan

In this work, we analyze a sublinear-time algorithm for selecting a few rows and columns of a matrix for low-rank approximation purposes. The algorithm is based on an initial uniformly random selection of rows and columns, followed by a…

Numerical Analysis · Mathematics 2024-02-22 Alice Cortinovis , Lexing Ying

Matrices with displacement structure such as Pick, Vandermonde, and Hankel matrices appear in a diverse range of applications. In this paper, we use an extremal problem involving rational functions to derive explicit bounds on the singular…

Numerical Analysis · Mathematics 2016-10-03 Bernhard Beckermann , Alex Townsend

We consider discretizations of the hyper-singular integral operator on closed surfaces and show that the inverses of the corresponding system matrices can be approximated by blockwise low-rank matrices at an exponential rate in the block…

Numerical Analysis · Mathematics 2017-12-04 Markus Faustmann , Jens Markus Melenk , Dirk Praetorius

The aim of this paper is to address two related estimation problems arising in the setup of hidden state linear time invariant (LTI) state space systems when the dimension of the hidden state is unknown. Namely, the estimation of any finite…

Statistics Theory · Mathematics 2022-02-04 Boualem Djehiche , Othmane Mazhar

A randomized algorithm for computing a compressed representation of a given rank-structured matrix $A \in \mathbb{R}^{N\times N}$ is presented. The algorithm interacts with $A$ only through its action on vectors. Specifically, it draws two…

Numerical Analysis · Mathematics 2024-06-25 James Levitt , Per-Gunnar Martinsson

A \emph{saddlepoint} of an $n \times n$ matrix is an entry that is the maximum of its row and the minimum of its column. Saddlepoints give the \emph{value} of a two-player zero-sum game, corresponding to its pure-strategy Nash equilibria;…

Computational Complexity · Computer Science 2024-01-17 Justin Dallant , Frederik Haagensen , Riko Jacob , László Kozma , Sebastian Wild

We study distributed low rank approximation in which the matrix to be approximated is only implicitly represented across the different servers. For example, each of $s$ servers may have an $n \times d$ matrix $A^t$, and we may be interested…

Numerical Analysis · Computer Science 2016-01-29 David P. Woodruff , Peilin Zhong

We propose a scheme for recycling Gaussian random vectors into structured matrices to approximate various kernel functions in sublinear time via random embeddings. Our framework includes the Fastfood construction as a special case, but also…

Machine Learning · Computer Science 2016-05-31 Krzysztof Choromanski , Vikas Sindhwani

This work presents a comprehensive understanding of the estimation of a planted low-rank signal from a general spiked tensor model near the computational threshold. Relying on standard tools from the theory of large random matrices, we…

Machine Learning · Statistics 2025-01-15 Hugo Lebeau , Florent Chatelain , Romain Couillet