Power-law dynamic arising from machine learning

DOI10.1007/978-981-19-4672-1_18zbMath1497.60086OpenAlexW4297571809MaRDI QIDQ2088480

Weitao Du, Qi Meng, Wei Chen, Zhi-Ming Ma

Publication date: 22 October 2022

Full work available at URL: https://doi.org/10.1007/978-981-19-4672-1_18

zbMATH Keywords

stochastic differential equationmachine learningstochastic gradient descentpower-law dynamic

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Stochastic partial differential equations (aspects of stochastic analysis) (60H15)

Uses Software

• ImageNet
• Tensor2Tensor
• AlexNet
• WaveNet

Cites Work

• Unnamed Item
• AlexNet
• Kramers escape rate in overdamped systems with the power-law distribution
• Semiclassical analysis for diffusions and stochastic processes
• Classical large deviation theorems on complete Riemannian manifolds
• Analysis for Diffusion Processes on Riemannian Manifolds
• Kramers' law: Validity, derivations and generalisations
• Power-law distributions and fluctuation-dissipation relation in the stochastic dynamics of two-variable Langevin equations
• Applied Stochastic Analysis

This page was built for publication: Power-law dynamic arising from machine learning