Partitioned Tensor Factorizations for Learning Mixed Membership Models
Abstract
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 $O(p^3)$ tensor, to factorizing $O(p/k)$ sub-tensors each of size $O(k^3)$. 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.
Cite
Text
Tan and Mukherjee. "Partitioned Tensor Factorizations for Learning Mixed Membership Models." International Conference on Machine Learning, 2017.Markdown
[Tan and Mukherjee. "Partitioned Tensor Factorizations for Learning Mixed Membership Models." International Conference on Machine Learning, 2017.](https://mlanthology.org/icml/2017/tan2017icml-partitioned/)BibTeX
@inproceedings{tan2017icml-partitioned,
title = {{Partitioned Tensor Factorizations for Learning Mixed Membership Models}},
author = {Tan, Zilong and Mukherjee, Sayan},
booktitle = {International Conference on Machine Learning},
year = {2017},
pages = {3358-3367},
volume = {70},
url = {https://mlanthology.org/icml/2017/tan2017icml-partitioned/}
}