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 2505.08062math.PR
收藏

全连接神经网络中协方差过程的大偏差原理(LDP)

LDP for the covariance process in fully connected neural networks

Luisa Andreis, Federico Bassetti, Christian Hirsch

AI总结:

本文在泛函框架下建立全连接高斯深度神经网络协方差过程的 LDP,并据此推出无限宽与平均场机制下高斯似然的后验 LDP。

摘要:

在这项工作中,我们研究全连接高斯深度神经网络中协方差过程的大偏差性质。更确切地说,我们在泛函框架中建立了协方差过程的大偏差原理(LDP),将其视为连续函数空间中的过程。作为主要结果的关键应用,我们在无限宽和平均场两种机制下,均得到了高斯似然下的后验 LDP。该证明基于协方差过程作为一个 Markov 过程的 LDP,该过程取值于赋予迹范数的非负对称迹类算子空间。

英文摘要:

In this work, we study large deviation properties of the covariance process in fully connected Gaussian deep neural networks. More precisely, we establish a large deviation principle (LDP) for the covariance process in a functional framework, viewing it as a process in the space of continuous functions. As key applications of our main results, we obtain posterior LDPs under Gaussian likelihood in both the infinite-width and mean-field regimes. The proof is based on an LDP for the covariance process as a Markov process valued in the space of non-negative, symmetric trace-class operators equipped with the trace norm.

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。

↑