The paper introduces a non-negative DAG learning formulation solved via method of multipliers, with proofs that the true DAG is the unique global minimizer and only acyclic KKT point in the population regime.
DAGMA: Learning DAGs via M-matrices and a log-determinant acyclicity characterization,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Exploiting Non-Negativity in DAG Structure Learning
The paper introduces a non-negative DAG learning formulation solved via method of multipliers, with proofs that the true DAG is the unique global minimizer and only acyclic KKT point in the population regime.