On the locality of the natural gradient for learning in deep Bayesian networks
From MaRDI portal
Publication:6115102
DOI10.1007/s41884-020-00038-yarXiv2005.10791MaRDI QIDQ6115102
Publication date: 12 July 2023
Published in: Information Geometry (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2005.10791
Related Items
Invariance properties of the natural gradient in overparametrised systems, Parametrisation independence of the natural gradient in overparametrised systems
Cites Work
- Information geometry and its applications
- Connectionist learning of belief networks
- Gradient systems in view of information geometry
- Expressions for the Moore-Penrose inverse of block matrices involving the Schur complement
- Algebraic Geometry and Statistical Learning Theory
- Riemannian metrics for neural networks I: feedforward networks
- Locality of Global Stochastic Interaction in Directed Acyclic Networks
- Information Geometry
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item