License: Creative Commons Attribution 4.0 International license (CC BY 4.0)
When quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.ICALP.2023.72
URN: urn:nbn:de:0030-drops-181246
URL: https://drops.dagstuhl.de/opus/volltexte/2023/18124/
Go to the corresponding LIPIcs Volume Portal


Harris, David G. ; Kolmogorov, Vladimir

Parameter Estimation for Gibbs Distributions

pdf-format:
LIPIcs-ICALP-2023-72.pdf (0.9 MB)


Abstract

A central problem in computational statistics is to convert a procedure for sampling combinatorial objects into a procedure for counting those objects, and vice versa. We will consider sampling problems which come from Gibbs distributions, which are families of probability distributions over a discrete space Ω with probability mass function of the form μ^Ω_β(ω) ∝ e^{β H(ω)} for β in an interval [β_min, β_max] and H(ω) ∈ {0} ∪ [1, n].
The partition function is the normalization factor Z(β) = ∑_{ω ∈ Ω} e^{β H(ω)}, and the log partition ratio is defined as q = (log Z(β_max))/Z(β_min)
We develop a number of algorithms to estimate the counts c_x using roughly Õ(q/ε²) samples for general Gibbs distributions and Õ(n²/ε²) samples for integer-valued distributions (ignoring some second-order terms and parameters), We show this is optimal up to logarithmic factors. We illustrate with improved algorithms for counting connected subgraphs and perfect matchings in a graph.

BibTeX - Entry

@InProceedings{harris_et_al:LIPIcs.ICALP.2023.72,
  author =	{Harris, David G. and Kolmogorov, Vladimir},
  title =	{{Parameter Estimation for Gibbs Distributions}},
  booktitle =	{50th International Colloquium on Automata, Languages, and Programming (ICALP 2023)},
  pages =	{72:1--72:21},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-278-5},
  ISSN =	{1868-8969},
  year =	{2023},
  volume =	{261},
  editor =	{Etessami, Kousha and Feige, Uriel and Puppis, Gabriele},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/opus/volltexte/2023/18124},
  URN =		{urn:nbn:de:0030-drops-181246},
  doi =		{10.4230/LIPIcs.ICALP.2023.72},
  annote =	{Keywords: Gibbs distribution, sampling}
}

Keywords: Gibbs distribution, sampling
Collection: 50th International Colloquium on Automata, Languages, and Programming (ICALP 2023)
Issue Date: 2023
Date of publication: 05.07.2023


DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI