Yichen Wu
Yichen Wu has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Ankur Moitra
Institute for Advanced Study Princeton University
1 shared publication - David Mimno
Princeton U Dept. of Computer Science 35 Olden St. 08540 Princeton NJ USA
1 shared publication - David Sontag
Courant Institute of Mathematical Sciences New York University
1 shared publication - Michael Zhu1 shared publication
- Rong Ge
Princeton University
1 shared publication - Sanjeev Arora
Department of Computer Science Princeton University
1 shared publication
Latest Publications
- Open Access
A Practical Algorithm for Topic Modeling with Provable Guarantees
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.
Open AccessA Practical Algorithm for Topic Modeling with Provable Guarantees
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.