For deep linear networks satisfying an alignment condition, the authors derive exact critical regularization strengths β_c = η_j at which each singular direction of the data covariance becomes learnable, via Landau-type effective potentials in the layer singular values.
Menon, The geometry of the deep linear network, inXIV Symposium on Probability and Stochastic Pro- cesses, edited by C
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cond-mat.stat-mech 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Cascading Through the Hierarchy: Regularizer-Induced Feature Detection as Phase Transitions in Deep Linear Neural Networks
For deep linear networks satisfying an alignment condition, the authors derive exact critical regularization strengths β_c = η_j at which each singular direction of the data covariance becomes learnable, via Landau-type effective potentials in the layer singular values.