English
Related papers

Related papers: Improved guarantees and a multiple-descent curve f…

200 papers

In this paper, we consider the optimization problem \scpl (\scp), which is to find a minimum cost subset of a ground set $U$ such that the value of a submodular function $f$ is above a threshold $\tau$. In contrast to most existing work on…

Data Structures and Algorithms · Computer Science 2022-11-10 Victoria G. Crawford

We study the low rank approximation problem of any given matrix $A$ over $\mathbb{R}^{n\times m}$ and $\mathbb{C}^{n\times m}$ in entry-wise $\ell_p$ loss, that is, finding a rank-$k$ matrix $X$ such that $\|A-X\|_p$ is minimized. Unlike…

Machine Learning · Computer Science 2019-10-31 Chen Dan , Hong Wang , Hongyang Zhang , Yuchen Zhou , Pradeep Ravikumar

Symmetric positive semi-definite (SPSD) matrix approximation methods have been extensively used to speed up large-scale eigenvalue computation and kernel learning methods. The standard sketch based method, which we call the prototype model,…

Machine Learning · Computer Science 2016-12-13 Shusen Wang , Zhihua Zhang , Tong Zhang

Kernel mean embeddings are a powerful tool to represent probability distributions over arbitrary spaces as single points in a Hilbert space. Yet, the cost of computing and storing such embeddings prohibits their direct use in large-scale…

Machine Learning · Statistics 2022-06-16 Antoine Chatalic , Nicolas Schreuder , Alessandro Rudi , Lorenzo Rosasco

We investigate two new optimization problems -- minimizing a submodular function subject to a submodular lower bound constraint (submodular cover) and maximizing a submodular function subject to a submodular upper bound constraint…

Data Structures and Algorithms · Computer Science 2013-11-12 Rishabh Iyer , Jeff Bilmes

We address the subset selection problem for matrices, where the goal is to select a subset of $k$ columns from a "short-and-fat" matrix $X \in \mathbb{R}^{m \times n}$, such that the pseudoinverse of the sampled submatrix has as small…

Numerical Analysis · Mathematics 2025-07-29 Ivan Kozyrev , Alexander Osinsky

We develop two approaches for analyzing the approximation error bound for the Nystr\"{o}m method, one based on the concentration inequality of integral operator, and one based on the compressive sensing theory. We show that the…

Machine Learning · Computer Science 2015-09-28 Rong Jin , Tianbao Yang , Mehrdad Mahdavi , Yu-Feng Li , Zhi-Hua Zhou

Random Fourier features (RFF) represent one of the most popular and wide-spread techniques in machine learning to scale up kernel algorithms. Despite the numerous successful applications of RFFs, unfortunately, quite little is understood…

Machine Learning · Statistics 2019-02-12 Zoltan Szabo , Bharath K. Sriperumbudur

Random Fourier features is one of the most popular techniques for scaling up kernel methods, such as kernel ridge regression. However, despite impressive empirical results, the statistical properties of random Fourier features are still not…

Machine Learning · Computer Science 2018-05-22 Haim Avron , Michael Kapralov , Cameron Musco , Christopher Musco , Ameya Velingker , Amir Zandieh

In many areas of machine learning, it becomes necessary to find the eigenvector decompositions of large matrices. We discuss two methods for reducing the computational burden of spectral decompositions: the more venerable Nystom extension…

Machine Learning · Statistics 2011-07-22 Darren Homrighausen , Daniel J. McDonald

The problem of best subset selection in linear regression is considered with the aim to find a fixed size subset of features that best fits the response. This is particularly challenging when the total available number of features is very…

Methodology · Statistics 2023-11-28 Sarat Moka , Benoit Liquet , Houying Zhu , Samuel Muller

Kernel methods are powerful and flexible approach to solve many problems in machine learning. Due to the pairwise evaluations in kernel methods, the complexity of kernel computation grows as the data size increases; thus the applicability…

Machine Learning · Computer Science 2017-11-28 Bharath Bhushan Damodaran , Nicolas Courty , Philippe-Henri Gosselin

We consider the Low Rank Approximation problem, where the input consists of a matrix $A \in \mathbb{R}^{n_R \times n_C}$ and an integer $k$, and the goal is to find a matrix $B$ of rank at most $k$ that minimizes $\| A - B \|_0$, which is…

Data Structures and Algorithms · Computer Science 2023-11-03 Vincent Cohen-Addad , Chenglin Fan , Suprovat Ghoshal , Euiwoong Lee , Arnaud de Mesmay , Alantha Newman , Tony Chang Wang

This paper investigates the column generation (CG) for solving cutting stock problems (CSP). Traditional CG method, which repeatedly solves a restricted master problem (RMP), often suffers from two critical issues in practice -- the loss of…

Optimization and Control · Mathematics 2023-05-24 Mingjie Hu , Jie Yan , Liting Chen , Qingwei Lin

Selecting diverse and important items, called landmarks, from a large set is a problem of interest in machine learning. As a specific example, in order to deal with large training sets, kernel methods often rely on low rank matrix Nystr\"om…

Machine Learning · Computer Science 2021-12-10 Michaël Fanuel , Joachim Schreurs , Johan A. K. Suykens

Dense subgraph discovery methods are routinely used in a variety of applications including the identification of a team of skilled individuals for collaboration from a social network. However, when the network's node set is associated with…

Social and Information Networks · Computer Science 2023-06-06 Atsushi Miyauchi , Tianyi Chen , Konstantinos Sotiropoulos , Charalampos E. Tsourakakis

The submodular knapsack problem (SKP), which seeks to maximize a submodular set function by selecting a subset of elements within a given budget, is an important discrete optimization problem. The majority of existing approaches to solving…

Data Structures and Algorithms · Computer Science 2025-07-16 Yimin Hao , Yi Zhou , Chao Xu , Zhang-Hua Fu

Optimization problems involving complex variables, when solved, are typically transformed into real variables, often at the expense of convergence rate and interpretability. This paper introduces a novel formalism for a prominent problem in…

Optimization and Control · Mathematics 2025-04-07 Raneem Madani , Abdel Lisser

We give the first algorithm for kernel Nystr\"om approximation that runs in *linear time in the number of training points* and is provably accurate for all kernel matrices, without dependence on regularity or incoherence conditions. The…

Machine Learning · Computer Science 2017-11-06 Cameron Musco , Christopher Musco

We derive error bounds for CUR matrix approximation using determinant-based methods that relate local projection errors to global approximation quality. For general matrices, we establish determinant identities for bordered Gramian matrices…

Numerical Analysis · Mathematics 2026-03-05 Frank de Hoog , Markus Hegland