A kernel encoder-decoder framework with error bounds is developed for multi-input/multi-output operator learning, and the KernelMO implementations beat or match neural operators on five parametric PDE families.
Álvarez, Lorenzo Rosasco, and Neil D
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Kernel Methods for Learning Operators with Multiple Inputs and Outputs
A kernel encoder-decoder framework with error bounds is developed for multi-input/multi-output operator learning, and the KernelMO implementations beat or match neural operators on five parametric PDE families.