arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.04166math.FAcs.LG

Approximation with Neural Networks in Variable Lebesgue Spaces

Technische Universität München(慕尼黑工业大学);Munich Center for Quantum Science and Technology(慕尼黑量子科学与技术中心);Universidad Autónoma de Madrid(马德里自治大学);Instituto de Ciencias Matemáticas(数学科学研究所)

Ángela Capel, Jesús Ocáriz

英文摘要:

This paper concerns the universal approximation property with neural networks in variable Lebesgue spaces. We show that, whenever the exponent function of the space is bounded, every function can be approximated with shallow neural networks with any desired accuracy. This result subsequently leads to determine the universality of the approximation depending on the boundedness of the exponent function. Furthermore, whenever the exponent is unbounded, we obtain some characterization results for the subspace of functions that can be approximated.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑