On the causality-preservation capabilities of generative modelling

DOI10.1016/J.CAM.2024.116312MaRDI QIDQ6653565zbMATH OpenFDO

Authors Yves-Cédric Bauwelinckx, J. Dhaene, Milan van den Heuvel, Tim Verdonck

Publication date 16 December 2024

Published in Journal of Computational and Applied Mathematics (Search for Journal in Brave)

zbMATH Keywords

synthetic datadata sciencecausalityshortcutgenerative adversarial networksgenerative modelling

Mathematics Subject Classification ID

Multivariate analysis (62Hxx) Actuarial science and mathematical finance (91Gxx) Artificial intelligence (68Txx)

Cites work

• A linear non-Gaussian acyclic model for causal discovery
• Distributionally robust unsupervised domain adaptation
• Estimation of a structural vector autoregression model using non-Gaussianity
• Estimation of causal effects using linear non-Gaussian causal models with hidden variables
• Quant GANs: deep generation of financial time series
• Sig‐Wasserstein GANs for conditional time series generation
• The curse of dimensionality in inverse problems

This page was built for publication: On the causality-preservation capabilities of generative modelling

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6653565)