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.
Symmetry in neural network parameter spaces
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
A complete classification of symmetries in shallow ReLU networks is achieved by using the non-differentiability of ReLU.
In overparameterized quadratic networks, one-pass SGD escapes generalization plateaus only modestly faster and selects the initialization-closest zero-loss solution due to a conserved quantity in the overlap ODEs.
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.
-
A Complete Symmetry Classification of Shallow ReLU Networks
A complete classification of symmetries in shallow ReLU networks is achieved by using the non-differentiability of ReLU.
-
Escape dynamics and implicit bias of one-pass SGD in overparameterized quadratic networks
In overparameterized quadratic networks, one-pass SGD escapes generalization plateaus only modestly faster and selects the initialization-closest zero-loss solution due to a conserved quantity in the overlap ODEs.