Explicit formulas for the codimension and component count of fiber varieties of the matrix multiplication map, with applications to deep linear networks and singular learning theory.
A convergence analysis of gradient descent for deep linear neural networks, 2019
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.AG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Geometry of fibers of the multiplication map of deep linear neural networks
Explicit formulas for the codimension and component count of fiber varieties of the matrix multiplication map, with applications to deep linear networks and singular learning theory.