Carregant...
Fitxers
Tipus de document
ArticleVersió
Versió publicadaData de publicació
Tots els drets reservats
Si us plau utilitzeu sempre aquest identificador per citar o enllaçar aquest document: https://hdl.handle.net/2445/213453
Neural Stochastic Differential Equations for conditional time series generation using the signature Wasserstein -1 metric
Títol de la revista
Director/Tutor
ISSN de la revista
Títol del volum
Recurs relacionat
Resum
(Conditional) generative adversarial networks (GANs) have had great success in recent years, due to their ability to approximate (conditional) distributions over extremely high-dimensional spaces. However, they are highly unstable and computationally expensive to train, especially in the time series setting. Recently, the use of a key object in rough path theory, called the signature of a path, has been proposed. This is able to convert the min–max formulation given by the (conditional) GAN framework into a classical minimization problem. However, this method is extremely costly in terms of memory, which can sometimes become prohibitive. To overcome this, we propose the use of conditional neural stochastic differential equations, designed to have a constant memory cost as a function of depth, being more memory efficient than traditional deep learning architectures. We empirically test the efficiency of our proposed model against other classical approaches, in terms of both memory cost and computational time, and show that it usually outperforms them according to several metrics.
Matèries (anglès)
Citació
Citació
DÍAZ, Pere, LOZANO, Toni, VIVES I SANTA EULÀLIA, Josep. Neural Stochastic Differential Equations for conditional time series generation using the signature Wasserstein -1 metric. _Journal Of Computational Finance_. 2023. Vol. 27, núm. 1, pàgs. 1-23. [consulta: 25 de febrer de 2026]. ISSN: 1460-1559. [Disponible a: https://hdl.handle.net/2445/213453]