DAGMA: Learning DAGs via M-matrices and a Log-Determinant Acyclicity Characterization Kevin Bello Bryon Aragam Pradeep Ravikumar Booth School of Business, University of Chicago, Chicago, IL60637

Nov-13-2025, 23:18:25 GMT–Neural Information Processing Systems 

Each point in the central path of DAGMA is a solution to an unconstrained problem regularized by our log-det function, then we show that at the limit of the central path the solution is guaranteed to be a DAG.