Compressing neural network by tensor network with exponentially fewer variational parameters

arXiv:2305.06058v2 Announce Type: replace
Abstract: Neural network (NN) designed for challenging machine learning tasks is in general a highly nonlinear mapping that contains massive variational parameters. High complexity of NN, if unbounded or unconstrained, might unpredictably cause severe issues including over-fitting, loss of generalization power, and unbearable cost of hardware. In this work, we propose a general compression scheme that significantly reduces the variational parameters of NN by encoding them to deep automatically-differentiable tensor network (ADTN) that contains exponentially-fewer free …

abstract arxiv complexity cost cs.ai cs.lg general loss machine machine learning mapping massive network neural network parameters power tasks tensor type