A natural-gradient optimizer that expands neural networks when their tangent space misaligns with the ideal Hilbert-space gradient reaches target accuracy on several toy regression, PDE, and model-reduction problems.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Expansive Natural Neural Gradient Flows for Energy Minimization
A natural-gradient optimizer that expands neural networks when their tangent space misaligns with the ideal Hilbert-space gradient reaches target accuracy on several toy regression, PDE, and model-reduction problems.