A Practical Algorithm for Topic Modeling with Provable Guarantees
Preprint
Abstract
Topic models provide a useful method for dimensionality reduction and exploratory data analysis in large text corpora. Most approaches to topic model inference have been based on a maximum likelihood objective. Efficient algorithms exist that approximate this objective, but they have no provable guarantees. Recently, algorithms have been introduced that provide provable bounds, but these algorithms are not practical because they are inefficient and not robust to violations of model assumptions. In this paper we present an algorithm for topic model inference that is both provable and practical. The algorithm produces results comparable to the best MCMC implementations while running orders of magnitude faster.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Robustness Analysis of Hottopixx, a Linear Programming Model for Factoring Nonnegative MatricesSIAM Journal on Matrix Analysis and Applications, 2013
- Learning Topic Models -- Going beyond SVD2012
- Efficient methods for topic model inference on streaming document collections2009
- Evaluation methods for topic models2009
- N‐FindR method versus independent component analysis for lithological identification in hyperspectral imageryInternational Journal of Remote Sensing, 2007
- A correlated topic model of ScienceThe Annals of Applied Statistics, 2007
- Vertex component analysis: a fast algorithm to unmix hyperspectral dataIEEE Transactions on Geoscience and Remote Sensing, 2005
- Finding scientific topicsProceedings of the National Academy of Sciences of the United States of America, 2004
- Exponentiated Gradient versus Gradient Descent for Linear PredictorsInformation and Computation, 1997
- Perturbation bounds in connection with singular value decompositionBIT Numerical Mathematics, 1972