Effect of Depth and Width on Local Minima in Deep Learning
Sign Up to like & getrecommendations! Published in 2019 at "Neural Computation"
DOI: 10.1162/neco_a_01195
Abstract: In this paper, we analyze the effects of depth and width on the quality of local minima, without strong overparameterization and simplification assumptions in the literature. Without any simplification assumption, for deep nonlinear neural networks… read more here.
Keywords: overparameterization; local minima; depth width; neural networks ... See more keywords