Time-changed normalizing flows for accurate SDE modeling - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year : 2023

Time-changed normalizing flows for accurate SDE modeling


The generative paradigm has become increasingly important in machine learning and deep learning models. Among popular generative models are normalizing flows, which enable exact likelihood estimation by transforming a base distribution through diffeomorphic transformations. Extending the normalizing flow framework to handle time-indexed flows gave dynamic normalizing flows, a powerful tool to model time series, stochastic processes, and neural stochastic differential equations (SDEs). In this work, we propose a novel variant of dynamic normalizing flows, a Time Changed Normalizing Flow (TCNF), based on time deformation of a Brownian motion which constitutes a versatile and extensive family of Gaussian processes. This approach enables us to effectively model some SDEs, that cannot be modeled otherwise, including standard ones such as the well-known Ornstein-Uhlenbeck process, and generalizes prior methodologies, leading to improved results and better inference and prediction capability.
Fichier principal
Vignette du fichier
Time_Change_Normalizing_Flow_vfinal.pdf (402.31 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04370186 , version 1 (02-01-2024)
hal-04370186 , version 2 (19-01-2024)





Naoufal El Bekri, Lucas Drumetz, Franck Vermet. Time-changed normalizing flows for accurate SDE modeling. 2023. ⟨hal-04370186v2⟩
51 View
30 Download



Gmail Facebook X LinkedIn More