Paperlane

no. 9 · Thursday 5 November 2026

Exact signal recovery from generative priors with sigmoid output activation

Matthew S. Scott, Yaniv Plan and Özgür Yılmaz

math.IT · 9 pp

Abstract

We show exact signal recovery in generative compressed sensing for feedforward neural networks with piecewise-linear activations and a final sigmoid activation, with no assumption of expansivity. Consider a ReLU network of depth $d$ with a sigmoid final activation, whose input layer, of dimension $k$, is the narrowest, and let $K$ be the geometric mean of the widths of its layers. We show that, with high probability, all signals of the range whose entries lie in $[δ, 1 - δ]$ are uniformly recovered from $m \gtrsim k(d \log(K/k) + \log(1+\log(1/δ)))$ measurements.

comments
9 pages
fields
Information Theory
pdf ↗ page arXiv:2611.05626 ↗