arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.00720cs.LGcs.NAmath.NAmath.OC
收藏

次齐次深度均衡模型

Subhomogeneous Deep Equilibrium Models

Gran Sasso Science Institute(格兰萨索科学研究所);University of Edinburgh(爱丁堡大学)

Pietro Sittoni, Francesco Tudisco

AI总结:

本文利用次齐次算子与非线性Perron-Frobenius理论分析隐式深度网络不动点的存在唯一性,在更弱参数假设下提出更灵活的次齐次网络,并在前馈、卷积和图神经网络上验证性能。

摘要:

近年来,隐式深度神经网络作为传统网络的有力替代方案,已在各种应用中得到发展。然而,这些模型往往缺乏存在性与唯一性保证,从而引发稳定性、性能和可复现性问题。本文基于次齐次算子概念和非线性 Perron-Frobenius 理论,对隐式深度神经网络不动点的存在性与唯一性进行了新的分析。与以往类似分析相比,我们的理论允许对参数矩阵施加更弱的假设,从而为良定义的隐式网络提供了一个更灵活的框架。我们通过前馈、卷积和图神经网络示例展示了所得次齐次网络的性能。

英文摘要:

Implicit-depth neural networks have grown as powerful alternatives to traditional networks in various applications in recent years. However, these models often lack guarantees of existence and uniqueness, raising stability, performance, and reproducibility issues. In this paper, we present a new analysis of the existence and uniqueness of fixed points for implicit-depth neural networks based on the concept of subhomogeneous operators and the nonlinear Perron-Frobenius theory. Compared to previous similar analyses, our theory allows for weaker assumptions on the parameter matrices, thus yielding a more flexible framework for well-defined implicit networks. We illustrate the performance of the resulting subhomogeneous networks on feedforward, convolutional, and graph neural network examples.

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。

↑