For ReLU networks with width at least two in input and hidden layers, an open set of parameters is identifiable, implying functional dimension equals parameter count minus hidden neurons.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
MLP training dynamics follow saddle-organized plateaus and near-optima before necessarily settling into an overfitting attractor on finite noisy datasets.
citing papers explorer
-
Most ReLU Networks Admit Identifiable Parameters
For ReLU networks with width at least two in input and hidden layers, an open set of parameters is identifiable, implying functional dimension equals parameter count minus hidden neurons.
-
Plateaus, Optima, and Overfitting in Multi-Layer Perceptrons: A Saddle-Saddle-Attractor Scenario
MLP training dynamics follow saddle-organized plateaus and near-optima before necessarily settling into an overfitting attractor on finite noisy datasets.