### Current browse context:

cs.LG

### Change to browse by:

### References & Citations

# Computer Science > Machine Learning

# Title: Depth separation beyond radial functions

(Submitted on 2 Feb 2021 (v1), last revised 22 Sep 2021 (this version, v4))

Abstract: High-dimensional depth separation results for neural networks show that certain functions can be efficiently approximated by two-hidden-layer networks but not by one-hidden-layer ones in high-dimensions $d$. Existing results of this type mainly focus on functions with an underlying radial or one-dimensional structure, which are usually not encountered in practice. The first contribution of this paper is to extend such results to a more general class of functions, namely functions with piece-wise oscillatory structure, by building on the proof strategy of (Eldan and Shamir, 2016). We complement these results by showing that, if the domain radius and the rate of oscillation of the objective function are constant, then approximation by one-hidden-layer networks holds at a $\mathrm{poly}(d)$ rate for any fixed error threshold.

A common theme in the proofs of depth-separation results is the fact that one-hidden-layer networks fail to approximate high-energy functions whose Fourier representation is spread in the domain. On the other hand, existing approximation results of a function by one-hidden-layer neural networks rely on the function having a sparse Fourier representation. The choice of the domain also represents a source of gaps between upper and lower approximation bounds. Focusing on a fixed approximation domain, namely the sphere $\mathbb{S}^{d-1}$ in dimension $d$, we provide a characterisation of both functions which are efficiently approximable by one-hidden-layer networks and of functions which are provably not, in terms of their Fourier expansion.

## Submission history

From: Luca Venturi [view email]**[v1]**Tue, 2 Feb 2021 17:25:02 GMT (75kb)

**[v2]**Wed, 3 Feb 2021 17:49:56 GMT (75kb)

**[v3]**Mon, 13 Sep 2021 18:02:57 GMT (74kb)

**[v4]**Wed, 22 Sep 2021 16:45:08 GMT (75kb)

Link back to: arXiv, form interface, contact.