LeCaSiM: Learning Causal Structure via Inverse of M-Matrices with Adjustable Coefficients

Abstract The objective of causal discovery is to uncover the causal relationships among natural phenomena or human behaviors, thus establishing the basis for subsequent prediction and inference. Traditional ways to reveal the causal structure between variables, such as interventions or random trials, are often deemed costly or impractical. With the diversity of means of data acquisition and abundant data, approaches that directly learn causal structure from observational data are attracting more interest in academia. Unfortunately, learning a directed acyclic graph (DAG) from samples of multiple variables has been proven to be a challenging problem. Recent proposals leverage the continuous optimization method to discover the structure of the target DAG from observational data using an acyclic constraint function. Although it has an elegant mathematical form, its optimization process is prone to numerical explosion or the disappearance of high-order gradients of constraint conditions, making the convergence conditions unstable and the result deviating from the true structure. To tackle these issues, we first combine the existing work to give a series of algebraic equivalent conditions for a DAG and its corresponding brief proofs, then leverage the properties of the M-matrix to derive a new acyclic constraint function. Based on the utilization of this function and linear structural equation models, we propose a novel causal discovery algorithm called LeCaSiM, which employs continuous optimization. Our algorithm exploits the spectral radius of the adjacency matrix to dynamically adjust the coefficients of the matrix polynomial, effectively solving the above problems. We conduct extensive experiments on both synthetic and real-world datasets, the results show our algorithm outperforms the existing algorithms on both computation time and accuracy under the same settings.