Every Local Minimum Value Is the Global Minimum Value of Induced Model in Nonconvex Machine Learning

DOI10.1162/neco_a_01234zbMath1494.68217arXiv1904.03673OpenAlexW3104627075WikidataQ90718207 ScholiaQ90718207MaRDI QIDQ5214402

Leslie Pack Kaelbling, Kenji Kawaguchi, Jiaoyang Huang

Publication date: 7 February 2020

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

Full work available at URL: https://arxiv.org/abs/1904.03673

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Nonconvex programming, global optimization (90C26) Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Unnamed Item
• Unnamed Item
• Stratification of real analytic mappings and images
• Gradient descent optimizes over-parameterized deep ReLU networks
• Stochastic subgradient method converges on tame functions
• Introduction to Smooth Manifolds
• Some NP-complete problems in quadratic and nonlinear programming
• Variational Analysis
• Gradient Descent with Identity Initialization Efficiently Learns Positive-Definite Linear Transformations by Deep Residual Networks
• Effect of Depth and Width on Local Minima in Deep Learning

This page was built for publication: Every Local Minimum Value Is the Global Minimum Value of Induced Model in Nonconvex Machine Learning