The gradient flow of recurrent networks can be written as -P K P* Err, and the low rank of K explains dynamic collapse to low-dimensional attractors.
Chen, Yulia Rubanova, Jesse Bettencourt, and David Duvenaud
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
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks
The gradient flow of recurrent networks can be written as -P K P* Err, and the low rank of K explains dynamic collapse to low-dimensional attractors.