Semi-Infinite Linear Regression and Its Applications

by   Paz Fink Shustin, et al.

Finite linear least squares is one of the core problems of numerical linear algebra, with countless applications across science and engineering. Consequently, there is a rich and ongoing literature on algorithms for solving linear least squares problems. In this paper, we explore a variant in which the system's matrix has one infinite dimension (i.e., it is a quasimatrix). We call such problems semi-infinite linear regression problems. As we show, the semi-infinite case arises in several applications, such supervised learning and function approximation, and allows for novel interpretations of existing algorithms. We explore semi-infinite linear regression rigorously and algorithmically. To that end, we give a formal framework for working with quasimatrices, and generalize several algorithms designed for finite problem to the infinite case. Finally, we suggest the use of various sampling methods for obtaining an approximate solution.


page 1

page 2

page 3

page 4


Fast, Provably convergent IRLS Algorithm for p-norm Linear Regression

Linear regression in ℓ_p-norm is a canonical optimization problem that a...

Linear regression in the Bayesian framework

These notes aim at clarifying different strategies to perform linear reg...

Approximate solutions of convex semi-infinite optimization problems in finitely many iterations

We develop two adaptive discretization algorithms for convex semi-infini...

Sparse Linear Regression via Generalized Orthogonal Least-Squares

Sparse linear regression, which entails finding a sparse solution to an ...

Reverse iterative volume sampling for linear regression

We study the following basic machine learning task: Given a fixed set of...

Determinantal Point Processes Implicitly Regularize Semi-parametric Regression Problems

Semi-parametric regression models are used in several applications which...

An Intrinsic Treatment of Stochastic Linear Regression

Linear regression is perhaps one of the most popular statistical concept...