no code implementations • 27 May 2024 • Francesco Montagna, Max Cairney-Leeming, Dhanya Sridhar, Francesco Locatello
Consistent with classical approaches, good performance is achieved when we have a good prior on the test data, and the underlying model is identifiable.
no code implementations • 22 Oct 2023 • Francesco Montagna, Nicoletta Noceti, Lorenzo Rosasco, Francesco Locatello
The use of simulated data in the field of causal discovery is ubiquitous due to the scarcity of annotated real data.
no code implementations • 6 Apr 2023 • Francesco Montagna, Nicoletta Noceti, Lorenzo Rosasco, Kun Zhang, Francesco Locatello
This paper demonstrates how to discover the whole causal graph from the second derivative of the log-likelihood in observational non-linear additive Gaussian noise models.
no code implementations • 6 Apr 2023 • Francesco Montagna, Nicoletta Noceti, Lorenzo Rosasco, Kun Zhang, Francesco Locatello
Causal discovery methods are intrinsically constrained by the set of assumptions needed to ensure structure identifiability.