Effect of Depth and Width on Local Minima in Deep Learning
Name
neco_a_01195.pdf
Description
Submitted version
Size
949.21 KB
Format
Unknown
Checksum (MD5)
964f2f0f086c50c70ee745d22bd37101
Author(s)
Kawaguchi, Kenji
Huang, Jiaoyang
Kaelbling, Leslie P
Date Issued
2019
Journal
Neural Computation
Publisher
MIT Press - Journals
Version
Original manuscript
Abstract
© 2019 Massachusetts Institute of Technology. For nonconvex optimization in machine learning, this article proves that every local minimum achieves the globally optimal value of the perturbable gradient basis model at any differentiable point. As a result, nonconvex machine learning is theoretically as supported as convex machine learning with a handcrafted basis in terms of the loss at differentiable local minima, except in the case when a preference is given to the handcrafted basis over the perturbable gradient basis. The proofs of these results are derived under mild assumptions. Accordingly, the proven results are directly applicable to many machine learning models, including practical deep neural networks, without any modification of practical methods. Furthermore, as special cases of our general results, this article improves or complements several state-of-the-art theoretical results on deep neural networks, deep residual networks, and overparameterized deep neural networks with a unified proof technique and novel geometric insights. A special case of our results also contributes to the theoretical foundation of representation learning.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution 4.0 International license
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1162/neco_a_01195
