This paper proposes a new classification model called logistic circuits. On MNIST and Fashion datasets, our learning algorithm outperforms neural networks that have an order of magnitude more parameters. Yet, logistic circuits have a distinct origin in symbolic AI, forming a discriminative counterpart to probabilistic-logical circuits such as ACs, SPNs, and PSDDs. We show that parameter learning for logistic circuits is convex optimization, and that a simple local search algorithm can induce strong model structures from data.

@inproceedings{LiangUDL18,
  author = {Liang, Yitao and Van den Broeck, Guy},
  title = {Learning Logistic Circuits},
  booktitle = {Proceedings of the UAI 2018 Workshop: Uncertainty in Deep Learning},
  url       = "http://starai.cs.ucla.edu/papers/LiangUDL18.pdf",
  month     = aug,
  year      = {2018},
  keywords  = {workshop,duplicate}
}