Thresholds of descending algorithms in inference problems
Machine Learning
2020-03-12 v2 Disordered Systems and Neural Networks
Machine Learning
Abstract
We review recent works on analyzing the dynamics of gradient-based algorithms in a prototypical statistical inference problem. Using methods and insights from the physics of glassy systems, these works showed how to understand quantitatively and qualitatively the performance of gradient-based algorithms. Here we review the key results and their interpretation in non-technical terms accessible to a wide audience of physicists in the context of related works.
Cite
@article{arxiv.2001.00479,
title = {Thresholds of descending algorithms in inference problems},
author = {Stefano Sarao Mannelli and Lenka Zdeborova},
journal= {arXiv preprint arXiv:2001.00479},
year = {2020}
}
Comments
8 pages, 4 figures