High-dimensional random landscapes: From typical to large deviations
SciPost Physics Lecture Notes · 2025
DOI: 10.21468/scipostphyslectnotes.102 ↗At a glance
Journal article in SciPost Physics Lecture Notes, 2025. Written by Valentina Ros. Cited 1 times so far (Crossref); 151 references. The full text is freely available (open access, CC BY 4.0).
Abstract (original language)
We discuss tools and concepts that emerge when studying high-dimensional random landscapes, i.e., random functions on high-dimensional spaces. As an illustrative example, we consider an inference problem in two forms: low-rank matrix estimation (case 1) and low-rank tensor estimation (case 2). We show how to map the inference problem onto the optimization problem of a high-dimensional landscape, which exhibits distinct geometrical properties in the two cases. We discuss methods for characterizing typical realizations of these landscapes and their optimization through local dynamics. We conclude by highlighting connections between the landscape problem and large deviation theory.
Cite
APA
Ros, V. (2025). High-dimensional random landscapes: From typical to large deviations. SciPost Physics Lecture Notes. https://doi.org/10.21468/scipostphyslectnotes.102
Vancouver
Ros V. High-dimensional random landscapes: From typical to large deviations. SciPost Physics Lecture Notes. 2025. doi:10.21468/scipostphyslectnotes.102
BibTeX
@article{Ros2025,
author = {Ros, Valentina},
title = {High-dimensional random landscapes: From typical to large deviations},
journal = {SciPost Physics Lecture Notes},
year = {2025},
doi = {10.21468/scipostphyslectnotes.102}
}
EUVIMED