Invariance properties of the natural gradient in overparametrised systems

DOI10.1007/s41884-022-00067-9arXiv2206.15273MaRDI QIDQ6115103

No author found.

Publication date: 12 July 2023

Published in: Information Geometry (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2206.15273

zbMATH Keywords

Riemannian metricinformation geometrynatural gradientdeep learning

Mathematics Subject Classification ID

Artificial intelligence (68Txx) Sufficiency and information (62Bxx)

Related Items (1)

Geometry and convergence of natural policy gradient methods

Cites Work

• Unnamed Item
• Stochastic approximation methods for constrained and unconstrained systems
• Wasserstein Riemannian geometry of Gaussian densities
• Natural gradient via optimal transport
• Parametrisation independence of the natural gradient in overparametrised systems
• Riemannian metrics for neural networks I: feedforward networks
• On the locality of the natural gradient for learning in deep Bayesian networks

This page was built for publication: Invariance properties of the natural gradient in overparametrised systems