On the convergence of formally diverging neural net-based classifiers

DOI10.1016/j.crma.2018.03.003zbMath1390.68516OpenAlexW2793287646MaRDI QIDQ1747388

Pierre-Emmanuel Jabin, Leonid Berlyand

Publication date: 8 May 2018

Published in: Comptes Rendus. Mathématique. Académie des Sciences, Paris (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.crma.2018.03.003

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Related Items

A novel multi-scale loss function for classification problems in machine learning, Stability for the training of deep neural networks and other classifiers

Uses Software

• ImageNet
• AlexNet

Cites Work

• Unnamed Item
• Subgeometric rates of convergence in Wasserstein distance for Markov chains
• Global-in-time weak measure solutions and finite-time aggregation for nonlocal interaction equations
• Asymptotic coupling and a general form of Harris' theorem with applications to stochastic delay equations
• Practical drift conditions for subgeometric rates of convergence.
• On asymptotics for Vaserstein coupling of Markov chains
• Subgeometric rates of convergence of Markov processes in the Wasserstein metric
• General relative entropy inequality: an illustration on growth models
• Group Invariant Scattering
• Markov Chains and Stochastic Stability
• Deep Haar scattering networks
• Lipschitz properties for deep convolutional networks