RSS Feed for "Scalable Parallel EM Algorithms for LDA in Multi Core Systems"-
Scalable Parallel EM Algorithms for LDA in Multi Core Systems 1.0.0
by anysubway - December 5, 2014, 10:18:36 CET [
]
view (2 today), download ( 1 today ), 0 subscriptions
- Description:
Latent Dirichlet allocation (LDA) is a widely-used probabilistic topic modeling tool for content analysis such as web mining. To handle web-scale content analysis on just a single PC, we propose multi-core parallel expectation-maximization (PEM) algorithms to infer and estimate LDA parameters in shared memory systems. By avoiding memory access conflicts, reducing the locking time among multiple threads and residual-based dynamic scheduling, we show that PEM algorithms are more scalable and accurate than the current state-of-the-art parallel LDA algorithms on a commodity PC.
- Changes to previous version:
Initial Announcement on mloss.org.
Comments
No one has posted any comments yet. Perhaps you'd like to be the first?
Leave a comment
You must be logged in to post comments.
Project details for Scalable Parallel EM Algorithms for LDA in Multi Core Systems
Manage
Details
- Version:
- 1.0.0
- Submitter:
- anysubway
- Author(s):
- Xiaosheng Liu , Jia Zeng , Xi Yang , Jianfeng Yan , Qiang Yang
- Posted:
- 5 December 2014
- Last Updated:
- 5 December 2014
- Open Source License:
- none
- Programming Language(s):
- c++