Mollifier Layers replace recursive autodiff with analytic mollifier convolutions, yielding efficient and noise-robust high-order derivatives for inverse PDE learning.
Neural ordinary differential equations
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
-
Mollifier Layers: Enabling Efficient High-Order Derivatives in Inverse PDE Learning
Mollifier Layers replace recursive autodiff with analytic mollifier convolutions, yielding efficient and noise-robust high-order derivatives for inverse PDE learning.