Depth Separation for Neural Networks
(1702.08489)Abstract
Let $f:\mathbb{S}{d-1}\times \mathbb{S}{d-1}\to\mathbb{S}$ be a function of the form $f(\mathbf{x},\mathbf{x}') = g(\langle\mathbf{x},\mathbf{x}'\rangle)$ for $g:[-1,1]\to \mathbb{R}$. We give a simple proof that shows that poly-size depth two neural networks with (exponentially) bounded weights cannot approximate $f$ whenever $g$ cannot be approximated by a low degree polynomial. Moreover, for many $g$'s, such as $g(x)=\sin(\pi d3x)$, the number of neurons must be $2{\Omega\left(d\log(d)\right)}$. Furthermore, the result holds w.r.t.\ the uniform distribution on $\mathbb{S}{d-1}\times \mathbb{S}{d-1}$. As many functions of the above form can be well approximated by poly-size depth three networks with poly-bounded weights, this establishes a separation between depth two and depth three networks w.r.t.\ the uniform distribution on $\mathbb{S}{d-1}\times \mathbb{S}{d-1}$.
We're not able to analyze this paper right now due to high demand.
Please check back later (sorry!).
Generate a summary of this paper on our Pro plan:
We ran into a problem analyzing this paper.