Achieve the Minimum Width of Neural Networks for Universal Approximation

Authors: Yongqiang Cai

ICLR 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We prove that both C-UAP and Lp-UAP for functions on compact domains share a universal lower bound of the minimal width; that is, w min = max(dx, dy).
Researcher Affiliation Academia Yongqiang Cai Beijing Normal University caiyq.math@bnu.edu.cn School of Mathematical Sciences, Laboratory of Mathematics and Complex Systems, MOE, Beijing Normal University, 100875 Beijing, China
Pseudocode No The paper does not contain any sections or figures explicitly labeled as 'Pseudocode' or 'Algorithm'.
Open Source Code No The paper is a theoretical work focusing on mathematical proofs and constructions, and therefore does not provide any associated source code.
Open Datasets No The paper is theoretical and focuses on mathematical proofs rather than empirical evaluation using datasets, so no information about publicly available datasets is provided.
Dataset Splits No The paper is theoretical and does not involve experimental validation using dataset splits.
Hardware Specification No The paper is theoretical and does not describe any experimental hardware specifications or computational resources used.
Software Dependencies No The paper is theoretical and focuses on mathematical concepts, therefore it does not list any specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not detail an experimental setup, including hyperparameters or training configurations.