Timezone: »

A polynomial-time algorithm for learning nonparametric causal graphs
Ming Gao · Yi Ding · Bryon Aragam

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #889
We establish finite-sample guarantees for a polynomial-time algorithm for learning a nonlinear, nonparametric directed acyclic graphical (DAG) model from data. The analysis is model-free and does not assume linearity, additivity, independent noise, or faithfulness. Instead, we impose a condition on the residual variances that is closely related to previous work on linear models with equal variances. Compared to an optimal algorithm with oracle knowledge of the variable ordering, the additional cost of the algorithm is linear in the dimension $d$ and the number of samples $n$. Finally, we compare the proposed algorithm to existing approaches in a simulation study.

Author Information

Ming Gao (the University of Chicago)
Yi Ding (University of Chicago)
Bryon Aragam (University of Chicago)

More from the Same Authors