Dynamical Systems Approach to Outlier Robust Deep Neural Networks for Regression

DOI10.1137/20M131727XzbMath1467.37075OpenAlexW3100794795MaRDI QIDQ4983517

Hannes Stuke, Pavel L. Gurevich

Publication date: 20 April 2021

Published in: SIAM Journal on Applied Dynamical Systems (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/20m131727x

zbMATH Keywords

outliersasymptoticsbifurcationlatent variablesKullback-Leibler divergenceregressionequilibriaconjugate priorsuncertainty quantificationStudent's \(t\)-distributiondeep neural networks

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) Simulation of dynamical systems (37M05) Computational methods for bifurcation problems in dynamical systems (37M20) Dynamical systems in numerical analysis (37N30)

Uses Software

• Edward
• Adam
• PRMLT
• Sever

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Robust Bayes estimation using the density power divergence
• Robust parameter estimation with a small bias against heavy contamination
• Hedonic housing prices and the demand for clean air
• A general method for robust Bayesian modeling
• Gradient conjugate priors and multi-layer neural networks
• Efficient learning with robust gradient descent
• Maximum L\(q\)-likelihood estimation
• Robust and efficient estimation by minimising a density power divergence
• Robust Estimation of a Location Parameter
• Robust Statistics

This page was built for publication: Dynamical Systems Approach to Outlier Robust Deep Neural Networks for Regression