📖
Annealed correlation and quenched noise sensitivity in biased deep neural networks
Johan Jonasson

Annealed correlation and quenched noise sensitivity in biased deep neural networks

Author / Organization:
Science & Mathematics Published 2026 Verification Pending

Overview & Synopsis

In earlier work by Jonasson, Steif and Zetterqvist (2023), fully connected deep neural networks with layers of width $n$, i.i.d.\ standard Gaussian weights, sign activations and no bias terms were shown to be annealed and quenched noise sensitive with respect to any joint probability distribution $\mathbb{Q}^{(n)}$ on the input $\boldsymbolω$ and its perturbation $\boldsymbolη$ satisfying a mild positive-correlation condition and $\mathbb{Q}^{(n)}(\boldsymbolη \in \{\boldsymbolω,-\boldsymbolω\}) \to 0$. Here we add independent Gaussian biases of the natural order and show that quenched noise sensitivity is retained over a broad range of depths, indeed under the slightly weaker assumption that $\mathbb{Q}^{(n)}(\boldsymbolω = \boldsymbolη) \to 0$. Thus, subject to the positive-correlation condition, quenched noise sensitivity holds under the minimal requirement that the perturbed input is asymptotically unlikely to coincide with the original input. At the same time, the annealed covariance remains bounded away from zero and is entirely accounted for by fluctuations in the network-dependent output means.

Indexed from repository: arXiv (arxiv.org)
Loading document from verified source...
Keyboard Shortcuts: ← / → for pages • + / - for zoom • 0 to fit width Powered by Mozilla PDF.js v3.11

Document Information

Document Title Annealed correlation and quenched noise sensitivity in biased deep neural networks
Author / Organization Johan Jonasson
Subject & Discipline stat.ML
Categories Science & Mathematics
Publication Year 2026
License / Rights arXiv Open Access / Creative Commons
Resource Verification Listed PDF (Verification Pending)
Original Host Website arXiv (arxiv.org)
File Format application/pdf (Portable Document Format)
Language EN
Catalog ID DOC-270583
Original Source Link Visit Source Page on arxiv.org »