Some exact results for the statistical physics problem of high-dimensional linear regression

by   Alexander Mozeika, et al.

High-dimensional linear regression have become recently a subject of many investigations which use statistical physics. The main bulk of this work relies on powerful approximation techniques but also a more rigorous approaches are becoming a more prominent. Considering Bayesian setting, we derive a number of exact results for the inference and related statistical physics problems of the linear regression.



page 1

page 2

page 3

page 4


A Model Free Perspective for Linear Regression: Uniform-in-model Bounds for Post Selection Inference

For the last two decades, high-dimensional data and methods have prolife...

An Intrinsic Treatment of Stochastic Linear Regression

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

High-dimensional robust regression and outliers detection with SLOPE

The problems of outliers detection and robust regression in a high-dimen...

Asymptotic normality in linear regression with approximately sparse structure

In this paper we study the asymptotic normality in high-dimensional line...

Tropical linear regression and mean payoff games: or, how to measure the distance to equilibria

We study a tropical linear regression problem consisting in finding the ...

Using parameter elimination to solve discrete linear Chebyshev approximation problems

We consider discrete linear Chebyshev approximation problems in which th...

On linear regression in three-dimensional Euclidean space

The three-dimensional linear regression problem is a problem of finding ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.