arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.13784stat.MLcs.LGmath.PR
收藏

机器学习算法泛化误差的一种新方法:估计与收敛性

A new approach to generalisation error of machine learning algorithms: Estimates and convergence

National Technical University of Athens(雅典国家技术大学);IACM-FORTH(希腊基础研究与技术基金会计算机科学研究所);University of Crete(克里特大学);University of Sussex(萨塞克斯大学)

Michail Loulakis, Charalambos G. Makridakis

AI总结:

本文研究深度神经学习模型问题,提出了一种在无神经网络结构假设下估计泛化误差并证明其收敛性的新方法。

摘要:

在这项工作中,我们考虑了一个深度神经学习的模型问题,即假设我们可以访问给定函数在有限点集上的点值时,对该给定函数进行学习。深度神经网络插值器是 f 的最终近似,它是通过涉及给定 DNN 架构和优化步骤的典型机器学习算法获得的,并假设该优化步骤被精确求解。这些是基于神经网络的最简单的回归算法之一。在这项工作中,我们引入了一种估计(泛化)误差和收敛性的新方法。我们的结果包括:(i) 在不对神经网络作任何结构假设,且仅对学习函数 f 施加温和的正则性假设的情况下,给出误差估计;(ii) 仅要求神经网络空间具备适当的逼近能力,即可实现近似对目标函数 f 的收敛。

英文摘要:

In this work we consider a model problem of deep neural learning, namely the learning of a given function when it is assumed that we have access to its point values on a finite set of points. The deep neural network interpolant is the the resulting approximation of f, which is obtained by a typical machine learning algorithm involving a given DNN architecture and an optimisation step, which is assumed to be solved exactly. These are among the simplest regression algorithms based on neural networks. In this work we introduce a new approach to the estimation of the (generalisation) error and to convergence. Our results include (i) estimates of the error without any structural assumption on the neural networks and under mild regularity assumptions on the learning function f (ii) convergence of the approximations to the target function f by only requiring that the neural network spaces have appropriate approximation capability.

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。

↑