Generalized Lyapunov exponents and aspects of the theory of deep learning

2022/12/26 by Anders Karlsson, Karlsson, Anders · 1 citation
Computer Science · Physics and Astronomy · #37A99 #37H15 #68T07 #Dynamical Systems (math.DS) #FOS: Mathematics #Model Reduction and Neural Networks #Neural Networks and Applications #Topological and Geometric Data Analysis

paper · pdf · doi:10.48550/arxiv.2212.13097

openalex publication_date 2022/12/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We discuss certain recent metric space methods and some of the possibilities these methods provide, with special focus on various generalizations of Lyapunov exponents originally appearing in the theory of dynamical systems and differential equations. These generalizations appear for example in topology, group theory, probability theory, operator theory and deep learning.

Cited by

• A horofunction counterpart to Teichmüller distance

Related

• Full Lyapunov Exponents spectrum with Deep Learning from single-variable time series
• Finite-time Lyapunov exponents of deep neural networks
• What are Lyapunov exponents, and why are they interesting?
• Lyapunov exponents in complex dynamics and potential theory
• Lyapunov exponents and Hodge theory