Random ReLU Neural Networks as Non-Gaussian Processes
Authors: Rahul Parhi, Pakshal Bohra, Ayoub El Biari, Mehrsa Pourya, Michael Unser
JMLR 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We prove that these random neural networks are well-defined non-Gaussian processes. As a by-product, we demonstrate that these networks are solutions to stochastic differential equations driven by impulsive white noise (combinations of random Dirac measures). ... The purpose of this paper is to study the properties of random neural networks as in (2) and (3)... |
| Researcher Affiliation | Academia | Department of Electrical and Computer Engineering University of California, San Diego La Jolla, CA 92093, USA Biomedical Imaging Group Ecole polytechnique f ed erale de Lausanne CH-1015 Lausanne, Switzerland |
| Pseudocode | No | The paper does not contain any explicitly labeled pseudocode or algorithm blocks. It describes a numerical generation procedure in Appendix D in paragraph and list format, but it is not presented as formal pseudocode or an algorithm block. |
| Open Source Code | No | The paper does not contain any explicit statements or links indicating that the source code for the methodology described is publicly available. |
| Open Datasets | No | The paper is theoretical in nature, focusing on the mathematical properties and analysis of random neural networks. It does not use or refer to any publicly available datasets for empirical evaluation. The numerical examples presented in Appendix D are realizations generated according to the theoretical models. |
| Dataset Splits | No | The paper does not involve empirical experiments using external datasets, and therefore, no training/test/validation dataset splits are mentioned. |
| Hardware Specification | No | The paper is primarily theoretical and presents numerical illustrations rather than empirical experiments. It does not provide any specific details about the hardware used, such as GPU/CPU models or other computing specifications. |
| Software Dependencies | No | The paper does not provide specific ancillary software details with version numbers (e.g., library or solver names with version numbers) that would be needed to replicate the numerical illustrations or any other part of the work. |
| Experiment Setup | No | The paper does not describe any empirical experimental setup, hyperparameters, or system-level training settings. The numerical examples are illustrative and do not involve explicit experimental configurations. |