Timezone: »

Conic Scan-and-Cover algorithms for nonparametric topic modeling
Mikhail Yurochkin · Aritra Guha · XuanLong Nguyen

Wed Dec 06 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #189 #None

We propose new algorithms for topic modeling when the number of topics is unknown. Our approach relies on an analysis of the concentration of mass and angular geometry of the topic simplex, a convex polytope constructed by taking the convex hull of vertices representing the latent topics. Our algorithms are shown in practice to have accuracy comparable to a Gibbs sampler in terms of topic estimation, which requires the number of topics be given. Moreover, they are one of the fastest among several state of the art parametric techniques. Statistical consistency of our estimator is established under some conditions.

Author Information

Mikhail Yurochkin (IBM Research AI)

I am working as a Research Staff Member at the IBM Research AI in Cambridge. Before, I have completed PhD in Statistics at the University of Michigan, advised by Prof. Long Nguyen. I received my bachelor degree in applied mathematics and physics from Moscow Institute of Physics and Technology.

Aritra Guha (University of Michigan)
Long Nguyen (University of Michigan)

More from the Same Authors