Regularization

TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization
We introduce TANGOS, a regularization method that orthogonalizes the gradient attribution of neurons to improve the generalization of deep neural networks on tabular data.
Alan Jeffares, Tennison Liu, Jonathan Crabbé, Fergus Imrie, Mihaela van der Schaar
PDF Cite Code Project
TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization