Depth Separation for Neural Networks under Gaussian Measure
arXiv:2610.28800v1 Announce Type: new Abstract: We revisit the problem of depth separation for neural networks, as studied by Eldan and Shamir, Daniely, and others. Specifically, we consider the natural setting of $L^2$ approximation of radial functions under the standard Gaussian measure in $d$ di…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-22 04:00 · arXiv stat.ML
Depth Separation for Neural Networks under Gaussian Measure