Department of Mathematics
 Search | Help | Login | pdf version | printable version

Math @ Duke



Publications [#335807] of Sayan Mukherjee

Papers Published

  1. Tan, Z; Mukherjee, S, Partitioned tensor factorizations for learning mixed membership models, 34th International Conference on Machine Learning, Icml 2017, vol. 7 (January, 2017), pp. 5156-5165, ISBN 9781510855144
    (last updated on 2018/10/06)

    Copyright © 2017 by the authors. We present an efficient algorithm for learning mixed membership models when the number of variables p is much larger than the number of hidden components k. This algorithm reduces the computational complexity of state-of-the-art tensor methods, which require decomposing an O (p3) tensor, to factorizing O (p/k) sub-tensors each of size O (k3). In addition, we address the issue of negative entries in the empirical method of moments based estimators. We provide sufficient conditions under which our approach has provable guarantees. Our approach obtains competitive empirical results on both simulated and real data.
ph: 919.660.2800
fax: 919.660.2821

Mathematics Department
Duke University, Box 90320
Durham, NC 27708-0320