A. Mozeika

F. Aguirre López

M. Sheikh

F. Antenucci

A. Coolen

Exact methods supersede approximations used in high-dimensional linear regression to find correlations in statistical physics problems.

High-dimensional linear regression has 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.

Exact results on high-dimensional linear regression via statistical physics