
A multiobjective continuation method is presented to efficiently compute the regularization path of high-dimensional deep neural networks, which connects the sparsest solution and the non-regularized solution.


coremsg

efficient-computation-of-the-regularization-path-for-high-dimensional-deep-neural-networks-using-multiobjective-continuation-methods


Efficient Computation of the Regularization Path for High-Dimensional Deep Neural Networks using Multiobjective Continuation Methods
