Manifoldron: Direct Space Partition via Manifold Discovery. (arXiv:2201.05279v1 [cs.LG])

A neural network with the widely-used ReLU activation has been shown to
partition the sample space into many convex polytopes for prediction. However,
the parameterized way a neural network and other machine learning models use to
partition the space has imperfections, e.g., the compromised interpretability
for complex models, the inflexibility in decision boundary construction due to
the generic character of the model, and the risk of being trapped into shortcut
solutions. In contrast, although the non-parameterized models can adorably
avoid …

arxiv discovery manifold space