Robust estimation of natural gradient in optimization by regularized linear regression

DOI10.1007/978-3-642-40020-9_97MaRDI QIDQ5410620zbMATH OpenOpenAlexFDO

Authors Luigi Malagò, Matteo Matteucci

Publication date 16 April 2014

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/978-3-642-40020-9_97

zbMATH Keywords

information geometrylassoregularized least squaresregularized natural gradientridge regressionstochastic gradient descent

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Stochastic programming (90C15) Approximation methods and heuristics in mathematical programming (90C59) Measures of information, entropy (94A17)

Recommendations

• Information Geometry of the Gaussian Distribution in View of Stochastic Optimization
• Improving Generalization Performance of Natural Gradient Learning Using Optimized Regularization by NIC
• Natural gradient for combined loss using wavelets
• Gradient flow of the stochastic relaxation on a generic exponential family
• scientific article; zbMATH DE number 3936292

Cited in

(2)

• Optimal transport natural gradient for statistical manifolds with continuous sample space
• Gradient flow of the stochastic relaxation on a generic exponential family

This page was built for publication: Robust estimation of natural gradient in optimization by regularized linear regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5410620)