2 papers
cs.LG2026
Regularization Implies balancedness in the deep linear network
Kathryn Lindsey, Govind Menon
We use geometric invariant theory (GIT) to study the deep linear network (DLN). The Kempf-Ness theorem is used to establish that the regularizer is minimized on the balanced…
cs.LG2024
On Functional Dimension and Persistent Pseudodimension
J. Elisenda Grigsby, Kathryn Lindsey
For any fixed feedforward ReLU neural network architecture, it is well-known that many different parameter settings can determine the same function. It is less well-known that the…