ML Anthology

Decentralized Approximate Bayesian Inference for Distributed Sensor Network

Behnam Gholami, Sejong Yoon, Vladimir Pavlovic
AAAI 2016 pp. 1582-1588
doi:10.1609/AAAI.V30I1.10201 /aaai/2016/gholami2016aaai-decentralized/

Abstract

Bayesian models provide a framework for probabilistic modelling of complex datasets. Many such models are computationally demanding, especially in the presence of large datasets. In sensor network applications, statistical (Bayesian) parameter estimation usually relies on decentralized algorithms, in which both data and computation are distributed across the nodes of the network. In this paper we propose a framework for decentralized Bayesian learning using Bregman Alternating Direction Method of Multipliers (B-ADMM). We demonstrate the utility of our framework, with Mean Field Variational Bayes (MFVB) as the primitive for distributed affine structure from motion (SfM).

PDF AAAI Semantic Scholar

Cite

Text

Gholami et al. "Decentralized Approximate Bayesian Inference for Distributed Sensor Network." AAAI Conference on Artificial Intelligence, 2016. doi:10.1609/AAAI.V30I1.10201

Markdown

[Gholami et al. "Decentralized Approximate Bayesian Inference for Distributed Sensor Network." AAAI Conference on Artificial Intelligence, 2016.](https://mlanthology.org/aaai/2016/gholami2016aaai-decentralized/) doi:10.1609/AAAI.V30I1.10201

BibTeX

@inproceedings{gholami2016aaai-decentralized,
  title     = {{Decentralized Approximate Bayesian Inference for Distributed Sensor Network}},
  author    = {Gholami, Behnam and Yoon, Sejong and Pavlovic, Vladimir},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2016},
  pages     = {1582-1588},
  doi       = {10.1609/AAAI.V30I1.10201},
  url       = {https://mlanthology.org/aaai/2016/gholami2016aaai-decentralized/}
}