Timezone: »

 
Poster
A Compositional Atlas of Tractable Circuit Operations for Probabilistic Inference
Antonio Vergari · YooJung Choi · Anji Liu · Stefano Teso · Guy Van den Broeck

Fri Dec 10 08:30 AM -- 10:00 AM (PST) @
in Poster Session 8 »

Circuit representations are becoming the lingua franca to express and reason about tractable generative and discriminative models. In this paper, we show how complex inference scenarios for these models that commonly arise in machine learning---from computing the expectations of decision tree ensembles to information-theoretic divergences of sum-product networks---can be represented in terms of tractable modular operations over circuits. Specifically, we characterize the tractability of simple transformations---sums, products, quotients, powers, logarithms, and exponentials---in terms of sufficient structural constraints of the circuits they operate on, and present novel hardness results for the cases in which these properties are not satisfied. Building on these operations, we derive a unified framework for reasoning about tractable models that generalizes several results in the literature and opens up novel tractable inference scenarios.

Keywords: Machine Learning

Author Information

Antonio Vergari (University of California, Los Angeles)
YooJung Choi (UCLA)
Anji Liu (University of California, Los Angeles)
Stefano Teso (University of Trento)
Guy Van den Broeck (UCLA)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors