A learned linear solver converges only to the projection of the true solution operator onto the training-data function space, and richer polynomial training data can actually increase the finite-difference parameter bias.
On the optimization of deep networks: Implicit acceleration by overparameterization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Interpretability and Generalization Bounds for Learning Spatial Physics
A learned linear solver converges only to the projection of the true solution operator onto the training-data function space, and richer polynomial training data can actually increase the finite-difference parameter bias.