Deep Bucket Elimination
Yasaman Razeghi, Kalev Kask, Yadong Lu, Pierre Baldi, Sakshi Agarwal, Rina Dechter
Abstract
Bucket Elimination (BE) is a universal inference scheme that can solve most tasks over probabilistic and deterministic graphical models exactly. However, it often requires exponentially high levels of memory (in the induced-width) preventing its execution. In the spirit of exploiting Deep Learning for inference tasks, in this paper, we will use neural networks to approximate BE. The resulting Deep Bucket Elimination (DBE) algorithm is developed for computing the partition function. We provide a proof-of-concept empirically using instances from several different benchmarks, showing that DBE can be a more accurate approximation than current state-of-the-art approaches for approximating BE (e.g. the mini-bucket schemes), especially when problems are sufficiently hard.
BibTeX
@inproceedings{ijcai2021p582,
title = {Deep Bucket Elimination},
author = {Razeghi, Yasaman and Kask, Kalev and Lu, Yadong and Baldi, Pierre and Agarwal, Sakshi and Dechter, Rina},
booktitle = {Proceedings of the Thirtieth International Joint Conference on
Artificial Intelligence, {IJCAI-21}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Zhi-Hua Zhou},
pages = {4235--4242},
year = {2021},
month = {8},
note = {Main Track},
doi = {10.24963/ijcai.2021/582},
url = {https://doi.org/10.24963/ijcai.2021/582},
}