The problem of processing very long time-series data (e.g., a length of more than 10,000) is a long-standing research problem in machine learning. Recently, one breakthrough, called neural rough differential equations (NRDEs), has been proposed and has shown that it is able to process such data. Their main concept is to use the log-signature transform, which is known to be more efficient than the Fourier transform for irregular long time-series, to convert a very long time-series sample into a relatively shorter series of feature vectors. However, the log-signature transform causes non-trivial spatial overheads. To this end, we present the method of LOweR-Dimensional embedding of log-signature (LORD), where we define an NRDE-based autoencoder to implant the higher-depth log-signature knowledge into the lower-depth log-signature. We show that the encoder successfully combines the higher-depth and the lower-depth log-signature knowledge, which greatly stabilizes the training process and increases the model accuracy. In our experiments with benchmark datasets, the improvement ratio by our method is up to 75\% in terms of various classification and forecasting evaluation metrics.
New directions in the applications of rough path theory
MINES ParisTech, PSL Research University(巴黎矿业学院,巴黎文理研究大学);Institut Curie, PSL Research University(居里研究所,巴黎文理研究大学);INSERM(法国国家健康与医学研究院);University of Oxford(牛津大学);The Alan Turing Institute(艾伦·图灵研究所);Imperial College London(伦敦帝国理工学院)
Rough Transformers: Lightweight and Continuous Time Series Modelling through Signature Patching
Oxford-Man Institute, University of Oxford(牛津大学牛津-曼研究所);Machine Learning Research Group, University of Oxford(牛津大学机器学习研究组);Mathematical Institute, University of Oxford(牛津大学数学研究所)
Branched Signature Kernel Solvers for ODEs with rough Single-Trajectory signals
Department of Mathematics, Florida State University(佛罗里达州立大学数学系);Department of Mathematics, Texas A&M University(德克萨斯大学阿姆斯特朗分校数学系);Department of Mathematics, Rutgers University(罗格斯大学数学系)
Rough Transformers for Continuous and Efficient Time-Series Modelling
Oxford-Man Institute of Quantitative Finance, University of Oxford(牛津大学牛津-曼数量金融研究所);Machine Learning Research Group, University of Oxford(牛津大学机器学习研究组);Mathematical Institute, University of Oxford(牛津大学数学研究所)
Scalable Signature Kernel Computations for Long Time Series via Local Neumann Series Expansions
Seminar for Applied Mathematics & AI Center ETH Zurich(应用数学与人工智能中心,苏黎世联邦理工学院);Department of Mathematics Technical University of Munich(数学系,慕尼黑技术大学);Department of Mathematics RWTH Aachen University(数学系,亚琛工业大学)