Probabilistic Inference with Algebraic Constraints: Theoretical Limits and Practical Approximations

Probabilistic Inference with Algebraic Constraints: Theoretical Limits and Practical Approximations (bibtex)

by Zhe Zeng, Paolo Morettin, Fanqi Yan, Antonio Vergari and Guy Van den Broeck

Reference:

Zhe Zeng, Paolo Morettin, Fanqi Yan, Antonio Vergari and Guy Van den Broeck. Probabilistic Inference with Algebraic Constraints: Theoretical Limits and Practical Approximations, In Advances in Neural Information Processing Systems 33 (NeurIPS), 2020.

Bibtex Entry:

@inproceedings{ZengNeurIPS20,
    title   = {Probabilistic Inference with Algebraic Constraints: Theoretical Limits and Practical Approximations},
    author = {Zeng, Zhe and Morettin, Paolo and Yan, Fanqi and Vergari, Antonio and Van den Broeck, Guy},
    booktitle = {Advances in Neural Information Processing Systems 33 (NeurIPS)},
    month   = {dec},
    year    = {2020},
    url     = "http://starai.cs.ucla.edu/papers/ZengNeurIPS20.pdf",
    slides    = "http://starai.cs.ucla.edu/slides/ZengNeurips20.pdf",
    video = "https://slideslive.com/38938005/probabilistic-inference-with-algebraic-constraints-theoretical-limits-and-practical-approximations",
    code = "https://github.com/UCLA-StarAI/recoin",
    keywords  = {conference,selective},
    annotation = "(Oral spotlight presentation, acceptance rate 385/9454 = 4.1\%)"
}

PDF Preview: