Deep Network Approximation for Smooth Functions

01/09/2020
by   Jianfeng Lu, et al.
0

This paper establishes optimal approximation error characterization of deep ReLU networks for smooth functions in terms of both width and depth simultaneously. To that end, we first prove that multivariate polynomials can be approximated by deep ReLU networks of width O(N) and depth O(L) with an approximation error O(N^-L). Through local Taylor expansions and their deep ReLU network approximations, we show that deep ReLU networks of width O(Nln N) and depth O(Lln L) can approximate f∈ C^s([0,1]^d) with a nearly optimal approximation rate O(f_C^s([0,1]^d)N^-2s/dL^-2s/d). Our estimate is non-asymptotic in the sense that it is valid for arbitrary width and depth specified by N∈N^+ and L∈N^+, respectively.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset