Combinatorial Topic Models using Small-Variance Asymptotics

Ke Jiang, Suvrit Sra, Brian Kulis
Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, PMLR 54:421-429, 2017.

Abstract

Modern topic models typically have a probabilistic formulation, and derive their inference algorithms based on Latent Dirichlet Allocation (LDA) and its variants. In contrast, we approach topic modeling via combinatorial optimization, and take a small-variance limit of LDA to derive a new objective function. We minimize this objective by using ideas from combinatorial optimization, obtaining a new, fast, and high-quality topic modeling algorithm. In particular, we show that our results are not only significantly better than traditional SVA algorithms, but also truly competitive with popular LDA-based approaches; we also discuss the (dis)similarities between our approach and its probabilistic counterparts.

Cite this Paper

BibTeX
@InProceedings{pmlr-v54-jiang17a, title = {{Combinatorial Topic Models using Small-Variance Asymptotics}}, author = {Jiang, Ke and Sra, Suvrit and Kulis, Brian}, booktitle = {Proceedings of the 20th International Conference on Artificial Intelligence and Statistics}, pages = {421--429}, year = {2017}, editor = {Singh, Aarti and Zhu, Jerry}, volume = {54}, series = {Proceedings of Machine Learning Research}, month = {20--22 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v54/jiang17a/jiang17a.pdf}, url = {https://proceedings.mlr.press/v54/jiang17a.html}, abstract = {Modern topic models typically have a probabilistic formulation, and derive their inference algorithms based on Latent Dirichlet Allocation (LDA) and its variants. In contrast, we approach topic modeling via combinatorial optimization, and take a small-variance limit of LDA to derive a new objective function. We minimize this objective by using ideas from combinatorial optimization, obtaining a new, fast, and high-quality topic modeling algorithm. In particular, we show that our results are not only significantly better than traditional SVA algorithms, but also truly competitive with popular LDA-based approaches; we also discuss the (dis)similarities between our approach and its probabilistic counterparts.} }
Endnote
%0 Conference Paper %T Combinatorial Topic Models using Small-Variance Asymptotics %A Ke Jiang %A Suvrit Sra %A Brian Kulis %B Proceedings of the 20th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2017 %E Aarti Singh %E Jerry Zhu %F pmlr-v54-jiang17a %I PMLR %P 421--429 %U https://proceedings.mlr.press/v54/jiang17a.html %V 54 %X Modern topic models typically have a probabilistic formulation, and derive their inference algorithms based on Latent Dirichlet Allocation (LDA) and its variants. In contrast, we approach topic modeling via combinatorial optimization, and take a small-variance limit of LDA to derive a new objective function. We minimize this objective by using ideas from combinatorial optimization, obtaining a new, fast, and high-quality topic modeling algorithm. In particular, we show that our results are not only significantly better than traditional SVA algorithms, but also truly competitive with popular LDA-based approaches; we also discuss the (dis)similarities between our approach and its probabilistic counterparts.
APA
Jiang, K., Sra, S. & Kulis, B.. (2017). Combinatorial Topic Models using Small-Variance Asymptotics. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 54:421-429 Available from https://proceedings.mlr.press/v54/jiang17a.html.

Related Material