Oral
Approximate Knowledge Compilation by Online Collapsed Importance Sampling
Tal Friedman · Guy Van den Broeck

Wed Dec 5th 04:25 -- 04:40 PM @ Room 220 E

We introduce collapsed compilation, a novel approximate inference algorithm for discrete probabilistic graphical models. It is a collapsed sampling algorithm that incrementally selects which variable to sample next based on the partial compila- tion obtained so far. This online collapsing, together with knowledge compilation inference on the remaining variables, naturally exploits local structure and context- specific independence in the distribution. These properties are used implicitly in exact inference, but are difficult to harness for approximate inference. More- over, by having a partially compiled circuit available during sampling, collapsed compilation has access to a highly effective proposal distribution for importance sampling. Our experimental evaluation shows that collapsed compilation performs well on standard benchmarks. In particular, when the amount of exact inference is equally limited, collapsed compilation is competitive with the state of the art, and outperforms it on several benchmarks.

Author Information

Tal Friedman (UCLA)
Guy Van den Broeck (UCLA)

I am an Assistant Professor and Samueli Fellow at UCLA, in the Computer Science Department, where I direct the Statistical and Relational Artificial Intelligence (StarAI) lab. My research interests are in Machine Learning (Statistical Relational Learning, Tractable Learning), Knowledge Representation and Reasoning (Graphical Models, Lifted Probabilistic Inference, Knowledge Compilation), Applications of Probabilistic Reasoning and Learning (Probabilistic Programming, Probabilistic Databases), and Artificial Intelligence in general.

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

More from the Same Authors