粗糙路径理论应用的新方向
New directions in the applications of rough path theory
摘要:
本文简要概述了粗糙路径理论在机器学习中应用的一些最新进展。控制微分方程(CDE)是描述流与物理控制系统相互作用的关键数学模型。在描述这种相互作用所产生的响应时,自然会出现一组称为签名的迭代积分。签名配备了各种强大的属性,使其成为流数据的理想特征映射。我们总结了深度学习和CDE之间共生关系的最新进展,研究了与RNN的联系,并最终提出了神经CDE模型。最后,我们讨论了签名核方法。
英文摘要:
This article provides a concise overview of some of the recent advances in the application of rough path theory to machine learning. Controlled differential equations (CDEs) are discussed as the key mathematical model to describe the interaction of a stream with a physical control system. A collection of iterated integrals known as the signature naturally arises in the description of the response produced by such interactions. The signature comes equipped with a variety of powerful properties rendering it an ideal feature map for streamed data. We summarise recent advances in the symbiosis between deep learning and CDEs, studying the link with RNNs and culminating with the Neural CDE model. We concluded with a discussion on signature kernel methods.
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。