Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

A general approximation lower bound in $L^p$ norm, with applications to feed-forward neural networks

Abstract : We study the fundamental limits to the expressive power of neural networks. Given two sets $F$, $G$ of real-valued functions, we first prove a general lower bound on how well functions in $F$ can be approximated in $L^p(\mu)$ norm by functions in $G$, for any $p \geq 1$ and any probability measure $\mu$. The lower bound depends on the packing number of $F$, the range of $F$, and the fat-shattering dimension of $G$. We then instantiate this bound to the case where $G$ corresponds to a piecewise-polynomial feed-forward neural network, and describe in details the application to two sets $F$: Hölder balls and multivariate monotonic functions. Beside matching (known or new) upper bounds up to log factors, our lower bounds shed some light on the similarities or differences between approximation in $L^p$ norm or in sup norm, solving an open question by DeVore et al. (2021). Our proof strategy differs from the sup norm case and uses a key probability result of Mendelson (2002).
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03690079
Contributor : Sébastien Gerchinovitz Connect in order to contact the contributor
Submitted on : Tuesday, June 7, 2022 - 6:59:33 PM
Last modification on : Monday, July 4, 2022 - 8:37:17 AM

Files

main.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03690079, version 1
  • ARXIV : 2206.04360

Citation

El Mehdi Achour, Armand Foucault, Sébastien Gerchinovitz, François Malgouyres. A general approximation lower bound in $L^p$ norm, with applications to feed-forward neural networks. 2022. ⟨hal-03690079⟩

Share

Metrics

Record views

51

Files downloads

11