English

A Bregman Method for Structure Learning on Sparse Directed Acyclic Graphs

Machine Learning 2020-11-06 v1 Machine Learning

Abstract

We develop a Bregman proximal gradient method for structure learning on linear structural causal models. While the problem is non-convex, has high curvature and is in fact NP-hard, Bregman gradient methods allow us to neutralize at least part of the impact of curvature by measuring smoothness against a highly nonlinear kernel. This allows the method to make longer steps and significantly improves convergence. Each iteration requires solving a Bregman proximal step which is convex and efficiently solvable for our particular choice of kernel. We test our method on various synthetic and real data sets.

Keywords

Cite

@article{arxiv.2011.02764,
  title  = {A Bregman Method for Structure Learning on Sparse Directed Acyclic Graphs},
  author = {Manon Romain and Alexandre d'Aspremont},
  journal= {arXiv preprint arXiv:2011.02764},
  year   = {2020}
}
R2 v1 2026-06-23T19:56:03.108Z