We present a method for learning Bayesian networks from data sets containing thousands of variables without the need for structure constraints. Our approach is made of two parts. The first is a novel algorithm that effectively explores the space of possible parent sets of a node. It guides the exploration towards the most promising parent sets on the basis of an approximated score function that is computed in constant time. The second part is an improvement of an existing ordering-based algorithm for structure optimization. The new algorithm provably achieves a higher score compared to its original formulation. Our novel approach consistently outperforms the state of the art on very large data sets.
|Title of host publication||Advances in Neural Information Processing Systems 28 (NIPS 2015)|
|Editors||C. Cortes, N.D. Lawrence, D.D. Lee, M. Sugiyama, R. Garnett|
|Publisher||NIPS Foundation, Inc|
|Number of pages||9|
|Publication status||Published - Dec 2015|
|Event||NIPS 2015 - Montreal, Canada|
Duration: 07 Dec 2015 → 12 Dec 2015
|Period||07/12/2015 → 12/12/2015|
Bibliographical noteDouble blind peer reviewed by multiple reviewers. Acc. rate 22%.
Scanagatta, M., de Campos, C. P., Corani, G., & Zaffalon, M. (2015). Learning Bayesian Networks with Thousands of Variables. In C. Cortes, N. D. Lawrence, D. D. Lee, M. Sugiyama, & R. Garnett (Eds.), Advances in Neural Information Processing Systems 28 (NIPS 2015) (pp. 1855-1863). NIPS Foundation, Inc. http://papers.nips.cc/paper/5803-learning-bayesian-networks-with-thousands-of-variables.pdf