Learning Logistic Circuits
This work addresses the problem of developing efficient and interpretable classification models for machine learning practitioners, offering a novel approach that bridges symbolic and statistical AI.
The paper introduces logistic circuits, a new classification model that outperforms neural networks with many more parameters on MNIST and Fashion datasets, achieving strong results through convex optimization and local search for structure learning.
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.