Hypertree Decompositions Revisited for PGMs
This addresses the problem of slow exact inference for researchers and practitioners in machine learning, though it is incremental as it builds on known database methods.
The paper tackles exact inference in probabilistic graphical models by introducing JoinInfer, an engine based on worst-case optimal join algorithms, which outperforms existing state-of-the-art engines by up to 630x on some benchmarks.
We revisit the classical problem of exact inference on probabilistic graphical models (PGMs). Our algorithm is based on recent worst-case optimal database join algorithms, which can be asymptotically faster than traditional data processing methods. We present the first empirical evaluation of these new algorithms via JoinInfer, a new exact inference engine. We empirically explore the properties of the data for which our engine can be expected to outperform traditional inference engines refining current theoretical notions. Further, JoinInfer outperforms existing state-of-the-art inference engines (ACE, IJGP and libDAI) on some standard benchmark datasets by up to a factor of 630x. Finally, we propose a promising data-driven heuristic that extends JoinInfer to automatically tailor its parameters and/or switch to the traditional inference algorithms.