Effect of Depth and Width on Local Minima in Deep Learning

DOI10.1162/neco_a_01195zbMath1494.68241arXiv1811.08150OpenAlexW2900832763WikidataQ92237572 ScholiaQ92237572MaRDI QIDQ5214354

Jiaoyang Huang, Leslie Pack Kaelbling, Kenji Kawaguchi

Publication date: 7 February 2020

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1811.08150

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Related Items

Learning constitutive relations using symmetric positive definite neural networks ⋮ Revisiting Landscape Analysis in Deep Neural Networks: Eliminating Decreasing Paths to Infinity ⋮ Optimization for deep learning: an overview ⋮ Every Local Minimum Value Is the Global Minimum Value of Induced Model in Nonconvex Machine Learning

Uses Software

• CIFAR

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Adaptive estimation of a quadratic functional by model selection.
• Linear models and generalizations. Least squares and alternatives. With contributions by Michael Schomaker.
• Some NP-complete problems in quadratic and nonlinear programming
• Universal approximation bounds for superpositions of a sigmoidal function