Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models

Chaoyue Liu · Libin Zhu · Mikhail Belkin

[ Abstract ]
[ Visit Poster at Spot F0 in Virtual World ] [ OpenReview
Mon 25 Apr 10:30 a.m. PDT — 12:30 p.m. PDT
Spotlight presentation:


Wide neural networks with linear output layer have been shown to be near-linear, and to have near-constant neural tangent kernel (NTK), in a region containing the optimization path of gradient descent. These findings seem counter-intuitive since in general neural networks are highly complex models. Why does a linear structure emerge when the neural networks become wide? In this work, we provide a new perspective on this "transition to linearity" by considering a neural network as an assembly model recursively built from a set of sub-models corresponding to individual neurons. In this view, we show that the linearity of wide neural networks is, in fact, an emerging property of assembling a large number of diverse ``weak'' sub-models, none of which dominate the assembly.

Chat is not available.