Neural network training under semidefinite constraints. (arXiv:2201.00632v1 [cs.LG])

This paper is concerned with the training of neural networks (NNs) under
semidefinite constraints. This type of training problems has recently gained
popularity since semidefinite constraints can be used to verify interesting
properties for NNs that include, e.g., the estimation of an upper bound on the
Lipschitz constant, which relates to the robustness of an NN, or the stability
of dynamic systems with NN controllers. The utilized semidefinite constraints
are based on sector constraints satisfied by the underlying activation
functions. …

arxiv network training neural network training