Size and Depth Separation in Approximating Benign Functions with Neural Networks release_v56bn7msrfe6ngltmxkhiqggr4

by Gal Vardi, Daniel Reichman, Toniann Pitassi, Ohad Shamir

Released as a article .

2021  

Abstract

When studying the expressive power of neural networks, a main challenge is to understand how the size and depth of the network affect its ability to approximate real functions. However, not all functions are interesting from a practical viewpoint: functions of interest usually have a polynomially-bounded Lipschitz constant, and can be computed efficiently. We call functions that satisfy these conditions "benign", and explore the benefits of size and depth for approximation of benign functions with ReLU networks. As we show, this problem is more challenging than the corresponding problem for non-benign functions. We give barriers to showing depth-lower-bounds: Proving existence of a benign function that cannot be approximated by polynomial-size networks of depth 4 would settle longstanding open problems in computational complexity. It implies that beyond depth 4 there is a barrier to showing depth-separation for benign functions, even between networks of constant depth and networks of nonconstant depth. We also study size-separation, namely, whether there are benign functions that can be approximated with networks of size O(s(d)), but not with networks of size O(s'(d)). We show a complexity-theoretic barrier to proving such results beyond size O(dlog^2(d)), but also show an explicit benign function, that can be approximated with networks of size O(d) and not with networks of size o(d/log d). For approximation in L_∞ we achieve such separation already between size O(d) and size o(d). Moreover, we show superpolynomial size lower bounds and barriers to such lower bounds, depending on the assumptions on the function. Our size-separation results rely on an analysis of size lower bounds for Boolean functions, which is of independent interest: We show linear size lower bounds for computing explicit Boolean functions with neural networks and threshold circuits.
In text/plain format

Archived Files and Locations

application/pdf  377.6 kB
file_dozjb4qmm5hr7k57w6h62ukbhm
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2021-06-28
Version   v3
Language   en ?
arXiv  2102.00314v3
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 1839f05b-5b2c-47e8-a436-1a59bc3c3b1b
API URL: JSON