activity
20182020
most citedLearning DAGs without imposing acyclicity

5 citations · 13 across the 3 of their papers we have counts for

collaborators

6 papers

stat.ML20205 cited

Learning DAGs without imposing acyclicity

Gherardo Varando

We explore if it is possible to learn a directed acyclic graph (DAG) from data without imposing explicitly the acyclicity constraint. In particular, for Gaussian distributions, we…

stat.ML20203 cited

Sparse Cholesky covariance parametrization for recovering latent structure in ordered data

Irene Córdoba, Concha Bielza, Pedro Larrañaga +1

The sparse Cholesky parametrization of the inverse covariance matrix can be interpreted as a Gaussian Bayesian network; however its counterpart, the covariance Cholesky factor, has…

stat.ML20205 cited

Graphical continuous Lyapunov models

Gherardo Varando, Niels Richard Hansen

The linear Lyapunov equation of a covariance matrix parametrizes the equilibrium covariance matrix of a stochastic process. This parametrization can be interpreted as a new graphic…

stat.ML2020

Causal structure learning from time series: Large regression coefficients may predict causal links better in practice than small p-values

Sebastian Weichwald, Martin E Jakobsen, Phillip B Mogensen +3

In this article, we describe the algorithms for causal structure learning from time series data that won the Causality 4 Climate competition at the Conference on Neural Information…

stat.ME2019

On generating random Gaussian graphical models

Irene Córdoba, Gherardo Varando, Concha Bielza +1

Structure learning methods for covariance and concentration graphs are often validated on synthetic models, usually obtained by randomly generating: (i) an undirected graph, and (i…

cs.LG2018

Markov Property in Generative Classifiers

Gherardo Varando, Concha Bielza, Pedro Larrañaga +1

We show that, for generative classifiers, conditional independence corresponds to linear constraints for the induced discrimination functions. Discrimination functions of undirecte…