Optimization on multifractal loss landscapes explains a diverse range of geometrical and dynamical properties of deep learning

Abstract Gradient descent and its variants are foundational in solving optimization problems across many disciplines. In deep learning, these optimizers demonstrate a remarkable ability to dynamically navigate complex loss landscapes, ultimately converging to solutions that generalize well. To eluci...

Full description

Saved in:
Bibliographic Details
Main Authors: Andrew Ly, Pulin Gong
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-025-58532-9
Tags: Add Tag
No Tags, Be the first to tag this record!