Overparameterization adds symmetries that precondition the Hessian for better minima and increase the probability mass of global minima near typical initializations.
Barriers for learning in an evolving world: Mathematical understanding of loss of plasticity
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
-
The Role of Symmetry in Optimizing Overparameterized Networks
Overparameterization adds symmetries that precondition the Hessian for better minima and increase the probability mass of global minima near typical initializations.