89 citations · 362 across the 53 of their papers we have counts for
3 papers · 2 filters
Topic Discovery through Data Dependent and Random Projections
Weicong Ding, Mohammad H. Rohban, Prakash Ishwar +1
We present algorithms for topic modeling based on the geometry of cross-document word-frequency patterns. This perspective gains significance under the so called separability condi…
A New Geometric Approach to Latent Topic Modeling and Discovery
Weicong Ding, Mohammad H. Rohban, Prakash Ishwar +1
A new geometrically-motivated algorithm for nonnegative matrix factorization is developed and applied to the discovery of latent "topics" for text and image "document" corpora. The…
An Impossibility Result for High Dimensional Supervised Learning
Mohammad Hossein Rohban, Prakash Ishwar, Birant Orten +2
We study high-dimensional asymptotic performance limits of binary supervised classification problems where the class conditional densities are Gaussian with unknown means and covar…