arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.07503stat.MLcs.LG
收藏

弱依赖下深度学习的超额风险界

Excess risk bound for deep learning under weak dependence

THEMA(THEMA(经济模型与应用理论实验室));CY Cergy Paris Université(CY巴黎塞尔吉大学)

William Kengne

摘要:

本文考虑在一般框架中用于学习弱依赖过程的深度神经网络,该框架包括例如回归估计、时间序列预测、时间序列分类。考虑的$ψ$ -弱依赖结构是相当大的,并涵盖了其他条件,如混合,关联,$\ldots$首先,光滑函数的近似深神经网络与广泛的一类激活函数。我们推导出深度神经网络所需的深度,宽度和稀疏性,以近似定义在任何紧集$\mx$上的任何Hölder光滑函数。其次,我们建立了深度神经网络学习弱相依观测值的超额风险界。当目标函数足够光滑时,该界接近于通常的$\mathcal{O}(n^{-1/2})$。

英文摘要:

This paper considers deep neural networks for learning weakly dependent processes in a general framework that includes, for instance, regression estimation, time series prediction, time series classification. The $ψ$-weak dependence structure considered is quite large and covers other conditions such as mixing, association,$\ldots$ Firstly, the approximation of smooth functions by deep neural networks with a broad class of activation functions is considered. We derive the required depth, width and sparsity of a deep neural network to approximate any Hölder smooth function, defined on any compact set $\mx$. Secondly, we establish a bound of the excess risk for the learning of weakly dependent observations by deep neural networks. When the target function is sufficiently smooth, this bound is close to the usual $\mathcal{O}(n^{-1/2})$.

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。

↑