Beats tuned baseline
2026
Learnable anisotropic Jacobian smoothing
Replace isotropic input-Jacobian regularization with a positive semidefinite, input-dependent metric learned jointly with the network. The metric uses diagonal scaling to suppress sensitivity in nuisance directions and a structured orthogonal rotation to discover combinations of input coordinates in which smoothness is task-useful.
Paper: PIEFS: Physics-Informed Eigenfunction Features with Learnable Scaling
arXiv:2607.03692