This is the code base for the paper:
"DAGs with No Fears: A Closer Look at Continuous Optimization for Learning Bayesian Networks." NeurIPS 2020
Paper PDF link: https://proceedings.neurips.cc/paper/2020/file/28a7602724ba16600d5ccc644c19bf18-Paper.pdf
python main_efficient.py
options:
--methods=all_l2
to call the baseline method, default value "all_l2" = NOTEAR, with L2 norm
--search=3
to call the proposed search method, default "3"", set to 0 to turn it off.
TODO