利用非负性在DAG结构学习中的应用
Exploiting Non-Negativity in DAG Structure Learning
AI总结:
本文研究了如何通过非负性约束简化DAG结构学习中的非凸优化问题,并提出了基于多pliers方法的正则化非负DAG学习算法,证明了在总体情况下真实DAG是唯一全局最小值点。
摘要:
本文研究了从节点观测数据学习有向无环图(DAG)的问题,这些数据由线性结构方程模型生成。DAG学习是信号处理、机器学习和因果推断中的核心任务,但其挑战在于无环性是一个全局组合性质。连续无环约束通过将离散DAG约束替换为光滑等式约束促进了算法进展。然而,现有方法仍然涉及困难的非凸优化景观并可能遭受退化的一阶最优条件。本文专注于具有非负边权的DAG,并利用此额外结构获得更简单的无环性表征。基于此表征,我们提出了一个正则化的非负DAG学习问题,并开发基于多pliers方法的算法。我们进一步分析了非负性诱导的良性优化景观。在总体情况下,我们证明真实DAG是所提出增广拉格朗日公式唯一的全局最小值点;此外,景观中没有虚假的内部 stationary 点,且真实DAG是唯一的无环KKT点。在合成和真实数据上的数值实验表明,所提方法优于现有连续DAG学习方法。
英文摘要:
This work addresses the problem of learning directed acyclic graphs (DAGs) from nodal observations adhering to a linear structural equation model. DAG structure learning is a central task in signal processing, machine learning, and causal inference, but it remains challenging because acyclicity is a global combinatorial property and the search space grows superexponentially in the number of nodes. Continuous acyclicity characterizations have led to important algorithmic advances by replacing the discrete DAG restriction with smooth equality constraints on the candidate adjacency matrix. However, existing formulations still involve difficult non-convex optimization landscapes and may suffer from degenerate first-order optimality conditions. Here, we restrict attention to DAGs with non-negative edge weights and exploit this additional structure to obtain a simpler acyclicity characterization devoid of Hadamard products. We propose a new non-negative constrained DAG estimator and develop a tractable, locally convergent algorithm based on the method of multipliers. We further analyze the benign optimization landscape induced by the non-negativity constraints. In the large-sample regime, we show that the true DAG is the unique global minimizer of the population augmented Lagrangian. Moreover, the landscape contains no spurious interior stationary points, and the true DAG is the only acyclic Karush--Kuhn--Tucker (KKT) point. Critically, this allows us to guarantee local convergence to the true DAG given infinite samples. Comprehensive numerical experiments show that the proposed structure identification method improves over state-of-the-art continuous DAG-learning baselines.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。