Low-Rank Boolean Matrix Approximation by Integer Programming

03/13/2018
by   Reka Kovacs, et al.
0

Low-rank approximations of data matrices are an important dimensionality reduction tool in machine learning and regression analysis. We consider the case of categorical variables, where it can be formulated as the problem of finding low-rank approximations to Boolean matrices. In this paper we give what is to the best of our knowledge the first integer programming formulation that relies on only polynomially many variables and constraints, we discuss how to solve it computationally and report numerical tests on synthetic and real-world data.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/27/2023

Practical Sketching Algorithms for Low-Rank Tucker Approximation of Large Tensors

Low-rank approximation of tensors has been widely used in high-dimension...
research
03/22/2019

CUR Decompositions, Approximations, and Perturbations

This article discusses a useful tool in dimensionality reduction and low...
research
08/29/2020

Computing low-rank approximations of the Fréchet derivative of a matrix function using Krylov subspace methods

The Fréchet derivative L_f(A,E) of the matrix function f(A) plays an imp...
research
11/09/2020

Binary Matrix Factorisation via Column Generation

Identifying discrete patterns in binary data is an important dimensional...
research
12/05/2019

KoPA: Automated Kronecker Product Approximation

We consider matrix approximation induced by the Kronecker product decomp...
research
02/21/2023

Boosting Nyström Method

The Nyström method is an effective tool to generate low-rank approximati...
research
10/06/2020

Gaussian Process Models with Low-Rank Correlation Matrices for Both Continuous and Categorical Inputs

We introduce a method that uses low-rank approximations of cross-correla...

Please sign up or login with your details

Forgot password? Click here to reset