English

Gaussian Process Topic Models

Machine Learning 2012-03-19 v1 Machine Learning

Abstract

We introduce Gaussian Process Topic Models (GPTMs), a new family of topic models which can leverage a kernel among documents while extracting correlated topics. GPTMs can be considered a systematic generalization of the Correlated Topic Models (CTMs) using ideas from Gaussian Process (GP) based embedding. Since GPTMs work with both a topic covariance matrix and a document kernel matrix, learning GPTMs involves a novel component-solving a suitable Sylvester equation capturing both topic and document dependencies. The efficacy of GPTMs is demonstrated with experiments evaluating the quality of both topic modeling and embedding.

Keywords

Cite

@article{arxiv.1203.3462,
  title  = {Gaussian Process Topic Models},
  author = {Amrudin Agovic and Arindam Banerjee},
  journal= {arXiv preprint arXiv:1203.3462},
  year   = {2012}
}

Comments

Appears in Proceedings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence (UAI2010)

R2 v1 2026-06-21T20:34:42.301Z