SparseLDA Algorithm
(Redirected from SparseLDA)
Jump to navigation
Jump to search
A SparseLDA Algorithm is an LDA Algorithm that efficiently evaluates Gibbs Sampling Distributions.
- AKA: SparseLDA.
- See: Gibbs Sampling Algorithm, LDA Algorithm.
References
2009
- (Yao et al., 2009) ⇒ Limin Yao, David Mimno, and Andrew McCallum. (2009). “Efficient Methods for Topic Model Inference on Streaming Document Collections.” In: Proceedings of ACM SIGKDD Conference (KDD-2009). 10.1145/1557019.1557121
- QUOTE: ... we present SparseLDA, an algorithm and data structure for evaluating Gibbs sampling distributions... Empirical results indicate that SparseLDA It can be approximately 20 times faster than traditional LDA ...
... since many of the methods we discuss rely on Gibbs sampling to infer topic distributions, we also present a simple method, SparseLDA, for efficient Gibbs sampling ...
.... The efficiency of Gibbs sampling-based inference methods depends almost entirely on how fast we can evaluate the sampling distribution over topics for a given token. We therefore present SparseLDA, our new algorithm and data structure that substantially improves sampling performance.
- QUOTE: ... we present SparseLDA, an algorithm and data structure for evaluating Gibbs sampling distributions... Empirical results indicate that SparseLDA It can be approximately 20 times faster than traditional LDA ...