research area Methods and Algorithms
content type paperpublished September 2025

Identifiable Multi-View Causal Discovery Without Non-Gaussianity

AuthorsAmbroise Heurtebise†*, Omar Chehab‡, Pierre Ablin, Alexandre Gramfort†, Aapo Hyvärinen§

View publication

We propose a novel approach to linear causal discovery in the framework of multi-view Structural Equation Models (SEM). Our proposed model relaxes the well-known assumption of non-Gaussian disturbances by alternatively assuming diversity of variances over views, making it more broadly applicable. We prove the identifiability of all the parameters of the model without any further assumptions on the structure of the SEM other than it being acyclic. We further propose an estimation algorithm based on recent advances in multi-view Independent Component Analysis (ICA). The proposed methodology is validated through simulations and application on real neuroimaging data, where it enables the estimation of causal graphs between brain regions.

  • † Inria, CEA, University of Paris-Saclay, France
  • ‡ ENSAE, CREST, IP Paris, France
  • § University of Helsinki, Finland
  • * Equal Contributor

Related readings and updates.

Multi-View Causal Discovery without Non-Gaussianity: Identifiability and Algorithms

December 10, 2025research area Methods and Algorithms

Causal discovery is a difficult problem that typically relies on strong assumptions on the data-generating model, such as non-Gaussianity. In practice, many modern applications provide multiple related views of the same system, which has rarely been considered for causal discovery. Here, we leverage this multi-view structure to achieve causal discovery with weak assumptions. We propose a multi-view linear Structural Equation Model (SEM) that…

Read more

High Fidelity 3D Reconstructions with Limited Physical Views

November 29, 2021research area Computer Visionconference 3DV

Multi-view triangulation is the gold standard for 3D reconstruction from 2D correspondences, given known calibration and sufficient views. However in practice expensive multi-view setups — involving tens sometimes hundreds of cameras — are required to obtain the high fidelity 3D reconstructions necessary for modern applications. In this work we present a novel approach that leverages recent advances in 2D-3D lifting using neural shape priors…

Read more