Stability of Deep Neural Networks via Discrete Rough Paths

DOI10.1137/22M1472358MaRDI QIDQ5885832

Peter K. Friz, Christian Bayer, Nikolas Tapia

Publication date: 30 March 2023

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2201.07566

zbMATH Keywords

stability\(p\)-variationrough pathsresidual neural networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Stability theory for difference equations (39A30) Applications of rough analysis (60L90)

Uses Software

• NeuralCDE
• torchcde
• Diffrax

Cites Work

• Integrability and tail estimates for Gaussian rough differential equations
• Strong and weak approximation of semilinear stochastic evolution equations
• Time-warping invariants of multidimensional time series
• Curvilinear integrals along enriched paths
• Differential equations driven by rough signals
• A priori estimates for rough PDEs with application to rough conservation laws
• Controlling rough paths
• Geometric versus non-geometric rough paths
• A proposal on machine learning via dynamical systems
• Multidimensional Stochastic Processes as Rough Paths
• Differential Equations Driven by Rough Paths: An Approach via Discrete Approximation
• Stable architectures for deep neural networks

This page was built for publication: Stability of Deep Neural Networks via Discrete Rough Paths