4 papers
Causal Discovery for Linear Non-Gaussian Models with Disjoint Cycles
Mathias Drton, Marina Garrote-López, Niko Nikov +2
The paradigm of linear structural equation modeling readily allows one to incorporate causal feedback loops in the model specification. These appear as directed cycles in the commo…
Robust Eigenvectors of Symmetric Tensors
Tommi Muller, Elina Robeva, Konstantin Usevich
The tensor power method generalizes the matrix power method to higher order arrays, or tensors. Like in the matrix case, the fixed points of the tensor power method are the eigenve…
Causal Structure Learning in Directed, Possibly Cyclic, Graphical Models
Pardis Semnani, Elina Robeva
We consider the problem of learning a directed graph from observational data. We assume that the distribution which gives rise to the samples is Markov and faithful to th…
Ultra-marginal Feature Importance: Learning from Data with Causal Guarantees
Joseph Janssen, Vincent Guan, Elina Robeva
Scientists frequently prioritize learning from data rather than training the best possible model; however, research in machine learning often prioritizes the latter. Marginal contr…