Under MSE training of deep linear networks, data augmentation and hard-wired invariance share global optima and critical points; regularization adds saddles and its solution path limits to the hard-wired optimum.
URL https://link.springer.com/10.1007/ 978-3-662-07931-7
1 Pith paper cite this work, alongside 55 external citations. Polarity classification is still indexing.
1
Pith paper citing it
55
external citations · OpenAlex
citation-role summary
other 1
citation-polarity summary
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Understanding Learning Invariance in Deep Linear Networks
Under MSE training of deep linear networks, data augmentation and hard-wired invariance share global optima and critical points; regularization adds saddles and its solution path limits to the hard-wired optimum.