Published in Neurips, 2019
This paper is about training SPENs using indirect supervision that comes from reward functions.
Recommended citation: Rooshenas, A., Zhang, D., Sharma, G., McCallum, A., ." Neurips 2019 1 http://rooshenas.github.io/files/sg_spen_neurips2019.pdf
Published in AIStats, 2016
This paper is about the importance of discriminative structure learning in comparison to discriminative parameter learning and generative learning for conditional arithemtic circuits.
Recommended citation: Rooshenas, A., Lowd, D., Discriminative Structure Learning of Arithmetic Circuits, In Proc. of 19th International Conference on Artificial Intelligence and Statistics (AISTATS), 2016. http://rooshenas.github.io/files/daclearn.pdf
Published in JMLR, 2015
The Libra Toolkit is a collection of algorithms for learning and inference with discrete probabilistic models. 
Recommended citation: D. Lowd and A. Rooshenas, The Libra Toolkit for Probabilistic Models, Journal of Machine Learning Research, 16:2459-2463, 2015 http://jmlr.org/papers/volume16/lowd15a/lowd15a.pdf
Published in ICML, 2014
This paper is about training SPENs using indirect supervision that comes from reward functions.
Recommended citation: Rooshenas, A., Lowd, D., Learning Sum-Product Networks with Direct and Indirect Variable Interactions, In Proc. of the Thirty-First International Conference on Machine Learning, 2014. http://proceedings.mlr.press/v32/rooshenas14.pdf