Research
Explicit integral representations and quantitative bounds for two-layer ReLU networks
arXiv:2604.23260v1 Announce Type: cross Abstract: An approach to construct explicit integral representations for two-layer ReLU networks is presented, which provides relatively simple representations
arXiv:2604.23260v1 Announce Type: cross Abstract: An approach to construct explicit integral representations for two-layer ReLU networks is presented, which provides relatively simple representations for any multivariate polynomial. Quantitative bounds are provided for a particular, sharpened ReLU integral representation, which involves a harmonic extension and a projection. The bounds demonstrate that functions can be approximated with L^{2}(D) errors that do not depend explicitly on dimension or degree, but rather the coefficients of their monomial expansions and the distribution D.
Related
- Sharp description of local minima in the loss landscape of high-dimensional two-layer ReLU neural networks
- Beyond ReLU: How Activations Affect Neural Kernels and Random Wide Networks
- Time-Frequency Analysis for Neural Networks
- Higher Order Approximation Rates for ReLU CNNs in Korobov Spaces
Source: arXiv cs.LG | 2026-04-28