Timezone: »

 
Spotlight
Complexity of Inference in Latent Dirichlet Allocation
David Sontag · Daniel Roy

Wed Dec 14 04:30 AM -- 04:34 AM (PST) @
in Spotlight Session 7 »

We consider the computational complexity of probabilistic inference in Latent Dirichlet Allocation (LDA). First, we study the problem of finding the maximum a posteriori (MAP) assignment of topics to words, where the document's topic distribution is integrated out. We show that, when the effective number of topics per document is small, exact inference takes polynomial time. In contrast, we show that, when a document has a large number of topics, finding the MAP assignment of topics to words in LDA is NP-hard. Next, we consider the problem of finding the MAP topic distribution for a document, where the topic-word assignments are integrated out. We show that this problem is also NP-hard. Finally, we briefly discuss the problem of sampling from the posterior, showing that this is NP-hard in one restricted setting, but leaving open the general question.

Author Information

David Sontag (MIT)
Daniel Roy (U of Toronto; Vector)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors