An alternative approach to train neural networks using monotone variational inequality

arXiv:2202.08876v4 Announce Type: replace-cross
Abstract: We propose an alternative approach to neural network training using the monotone vector field, an idea inspired by the seminal work of Juditsky and Nemirovski [Juditsky & Nemirovsky, 2019] developed originally to solve parameter estimation problems for generalized linear models (GLM) by reducing the original non-convex problem to a convex problem of solving a monotone variational inequality (VI). Our approach leads to computationally efficient procedures that converge fast and offer guarantee in some special cases, …

abstract arxiv cs.lg generalized inequality linear network networks network training neural network neural networks solve stat.ml train training type vector work