paper-with-me

홈 › Papers

Partitioned Tensor Factorizations for Learning Mixed Membership Models

2017-08-01 · ICML 2017 8 · Zilong Tan, Sayan Mukherjee

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On Mixed Memberships and Symmetric Nonnegative Matrix Factorizations

2016-07-01 · ICML 2017 8 · Xueyu Mao, Purnamrita Sarkar, Deepayan Chakrabarti

The problem of finding overlapping communities in networks has gained much attention recently. Optimization-based approaches use non-negative matrix factorization (NMF) or variants, but the global optimum cannot be prova…

Estimating Higher-Order Mixed Memberships via the $\ell_{2,\infty}$ Tensor Perturbation Bound

2022-12-16 · Joshua Agterberg, Anru Zhang

Higher-order multiway data is ubiquitous in machine learning and statistics and often exhibits community-like structures, where each component (node) along each different mode has a community membership associated with i…

Efficient Learning of Mixed Membership Models

2017-02-25 · Zilong Tan, Sayan Mukherjee

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 stat…

Learning Mixed Membership Community Models in Social Tagging Networks through Tensor Methods

2015-03-16 · Anima Anandkumar, Hanie Sedghi

Community detection in graphs has been extensively studied both in theory and in applications. However, detecting communities in hypergraphs is more challenging. In this paper, we propose a tensor decomposition approach …

Community DetectionTAGTensor Decomposition

A Tensor Approach to Learning Mixed Membership Community Models

2013-02-12 · Anima Anandkumar, Rong Ge, Daniel Hsu, Sham M. Kakade

Community detection is the task of detecting hidden communities from observed interactions. Guaranteed community detection has so far been mostly limited to models with non-overlapping communities such as the stochastic …

Community DetectionStochastic Block Model