Parametrisation independence of the natural gradient in overparametrised systems

DOI10.1007/978-3-030-80209-7_78MaRDI QIDQ2117935zbMATH OpenOpenAlexFDO

Authors Jesse van Oostrum, Nihat Ay

Publication date 22 March 2022

Full work available at URL https://doi.org/10.1007/978-3-030-80209-7_78

zbMATH Keywords

deep learninginformation geometryRiemannian metricnatural gradient

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Artificial neural networks and deep learning (68T07)

Cites work

• scientific article; zbMATH DE number 7306852 (Why is no real title available?)
• Algebraic Geometry and Statistical Learning Theory
• On the locality of the natural gradient for learning in deep Bayesian networks
• Riemannian metrics for neural networks. I: Feedforward networks

Cited in

(1)

• Invariance properties of the natural gradient in overparametrised systems

This page was built for publication: Parametrisation independence of the natural gradient in overparametrised systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2117935)