Support Consistency of Direct Sparse-Change Learning in Markov Networks

Abstract

We study the problem of learning sparse structure changes between two Markov networks P and Q. Rather than fitting two Markov networks separately to two sets of data and figuring out their differences, a recent work proposed to learn changes directly via estimating the ratio between two Markov network models.  Such a direct approach was demonstrated to perform excellently in experiments, although its theoretical properties remained unexplored.  In this paper, we give sufficient conditions for successful change detection with respect to the sample size np, nq, the dimension of data m, and the number of changed edges d.

Cite

Text

Liu et al. "Support Consistency of Direct Sparse-Change Learning in Markov Networks." AAAI Conference on Artificial Intelligence, 2015. doi:10.1609/AAAI.V29I1.9566

Markdown

[Liu et al. "Support Consistency of Direct Sparse-Change Learning in Markov Networks." AAAI Conference on Artificial Intelligence, 2015.](https://mlanthology.org/aaai/2015/liu2015aaai-support/) doi:10.1609/AAAI.V29I1.9566

BibTeX

@inproceedings{liu2015aaai-support,
  title     = {{Support Consistency of Direct Sparse-Change Learning in Markov Networks}},
  author    = {Liu, Song and Suzuki, Taiji and Sugiyama, Masashi},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2015},
  pages     = {2785-2791},
  doi       = {10.1609/AAAI.V29I1.9566},
  url       = {https://mlanthology.org/aaai/2015/liu2015aaai-support/}
}