Sig-Splines : Universal Approximation and Convex Calibration of Time Series Generative Models

We propose a novel generative model for multivariate discrete-time time series data. Drawing inspiration from the construction of neural spline flows, our algorithm incorporates linear transformations and the signature transform as a seamless substitution for traditional neural networks. This approach enables us to achieve not only the universality property inherent in neural networks but also introduces convexity in the model's parameters

Year of publication:	[2023]
Authors:	Wiese, Magnus ; Phillip, Murray ; Korn, Ralf
Publisher:	[S.l.] : SSRN
Subject:	Theorie \| Theory \| Zeitreihenanalyse \| Time series analysis
Description of contents:	Abstract [papers.ssrn.com]

Check Google Scholar |

More access options

In German libraries (KVK)

Which error do you want to report?

Report: URL of this record is broken

Please note: Sometimes more than one URL is available for a resource. Please click on "More Options" to display these URLs

Report: Addition of an URL to that resource

Please note: Sometimes more than one URL is available for a resource. Please click on "More Options" to display these URLs

Report: The language(s) of that resource is/are…

Please note: Required language not in the list? Please use comment field

Report: Addition of an identifier to that resource

Report: report typo

Report: Add statement

Report: Add keywords

Please use the commentary box to describe other errors

Would you like to receive a feedback?

Commentary

Please type the code from the image

For general questions please use this address.

Persistent link: https://www.econbiz.de/10014343773

A service of the