@Article{JML-1-60,
author = {Zhang , YaoyuLi , YuqingZhang , ZhongwangLuo , Tao and John Xu , Zhi-Qin},
title = {Embedding Principle: A Hierarchical Structure of Loss Landscape of Deep Neural Networks},
journal = {Journal of Machine Learning},
year = {2022},
volume = {1},
number = {1},
pages = {60--113},
abstract = {<p style="text-align: justify;">We prove a general Embedding Principle of loss landscape of deep neural networks (NNs) that
unravels a hierarchical structure of the loss landscape of NNs, i.e., loss landscape of an NN contains all critical
points of all the narrower NNs. This result is obtained by constructing a class of critical embeddings which
map any critical point of a narrower NN to a critical point of the target NN with the same output function.
By discovering a wide class of general compatible critical embeddings, we provide a gross estimate of the
dimension of critical submanifolds embedded from critical points of narrower NNs. We further prove an
irreversibility property of any critical embedding that the number of negative/zero/positive eigenvalues of
the Hessian matrix of a critical point may increase but never decrease as an NN becomes wider through
the embedding. Using a special realization of general compatible critical embedding, we prove a stringent
necessary condition for being a “truly-bad” critical point that never becomes a strict-saddle point through any
critical embedding. This result implies the commonplace of strict-saddle points in wide NNs, which may be
an important reason underlying the easy optimization of wide NNs widely observed in practice.</p>},
issn = {2790-2048},
doi = {https://doi.org/10.4208/jml.220108},
url = {http://global-sci.org/intro/article_detail/jml/20372.html}
}