LGDIS-NNMLJan 2, 2020

Thresholds of descending algorithms in inference problems

arXiv:2001.00479v24 citations
AI Analysis

This is an incremental review aimed at physicists, summarizing existing results without new contributions.

The paper reviews recent works that analyze the dynamics of gradient-based algorithms in statistical inference problems, using methods from glassy systems physics to understand their performance quantitatively and qualitatively.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes