Skip to yearly menu bar Skip to main content


In-Person Poster presentation / poster accept

DAG Learning on the Permutahedron

Valentina Zantedeschi · Luca Franceschi · Jean Kaddour · Matt Kusner · Vlad Niculae

MH1-2-3-4 #114

Keywords: [ causal discovery ] [ directed acyclic graph ] [ differentiable sorting ] [ General Machine Learning ]


Abstract:

We propose a continuous optimization framework for discovering a latent directed acyclic graph (DAG) from observational data. Our approach optimizes over the polytope of permutation vectors, the so-called Permutahedron, to learn a topological ordering. Edges can be optimized jointly, or learned conditional on the ordering via a non-differentiable subroutine. Compared to existing continuous optimization approaches our formulation has a number of advantages including: 1. validity: optimizes over exact DAGs as opposed to other relaxations optimizing approximate DAGs; 2. modularity: accommodates any edge-optimization procedure, edge structural parameterization, and optimization loss; 3. end-to-end: either alternately iterates between node-ordering and edge-optimization, or optimizes them jointly; We demonstrate, on real-world data problems in protein-signaling and transcriptional network discovery, that our approach lies on the Pareto frontier of two key metrics, the SID and SHD.

Chat is not available.