MLP training dynamics follow saddle-organized plateaus and near-optima before necessarily settling into an overfitting attractor on finite noisy datasets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.