Deterministic Single-Pass Algorithm for LDA

Abstract

We develop a deterministic single-pass algorithm for latent Dirichlet allocation (LDA) in order to process received documents one at a time and then discard them in an excess text stream. Our algorithm does not need to store old statistics for all data. The proposed algorithm is much faster than a batch algorithm and is comparable to the batch algorithm in terms of perplexity in experiments.

Cite

Text

Sato et al. "Deterministic Single-Pass Algorithm for LDA." Neural Information Processing Systems, 2010.

Markdown

[Sato et al. "Deterministic Single-Pass Algorithm for LDA." Neural Information Processing Systems, 2010.](https://mlanthology.org/neurips/2010/sato2010neurips-deterministic/)

BibTeX

@inproceedings{sato2010neurips-deterministic,
  title     = {{Deterministic Single-Pass Algorithm for LDA}},
  author    = {Sato, Issei and Kurihara, Kenichi and Nakagawa, Hiroshi},
  booktitle = {Neural Information Processing Systems},
  year      = {2010},
  pages     = {2074-2082},
  url       = {https://mlanthology.org/neurips/2010/sato2010neurips-deterministic/}
}