@COMMENT This file was generated by bib2html.pl <https://sourceforge.net/projects/bib2html/> version 0.94
@COMMENT written by Patrick Riley <http://sourceforge.net/users/patstg/>
@COMMENT This file came from Kuldeep S. Meel's publication pages at
@COMMENT http://www.comp.nus.edu.sg/~meel/publications/
@inproceedings{PM21,
  title={Testing Probabilistic Circuits},
  author={Pote, Yash and Meel, Kuldeep S.},
  booktitle=NIPS,
  month=dec,
  year={2021},
  bib2html_rescat={Distribution Testing},
  bib2html_dl_pdf={../Papers/neurips21-pm.pdf},
  bib2html_pubtype={Refereed Conference},
  abstract={
    Probabilistic circuits (PCs) are a powerful modeling framework for
    representing tractable probability distributions over combinatorial spaces.
    In machine learning and probabilistic programming, one is often interested
    in understanding whether the distributions learned using PCs are close to
    the desired distribution. Thus, given two probabilistic circuits, a
    fundamental problem of interest is to determine whether their distributions
    are close to each other.
    The primary contribution of this paper is a closeness test for PCs with
    respect to the total variation distance metric. Our algorithm utilizes two
    common PC queries, counting and sampling. In particular, we provide a
    poly-time probabilistic algorithm to check closeness of two PCs, when the
    PCs support tractable approximate counting and sampling. We demonstrate the
    practical efficiency of our algorithmic framework via a detailed
    experimental evaluation of a prototype implementation against a set of 100
    PC benchmarks. We find that our test correctly decides the closeness of all
    100 PCs within 3600 seconds.
  },
}