资源论文Clustering by Left-Stochastic Matrix Factorization

Clustering by Left-Stochastic Matrix Factorization

2020-02-27 | |  129 |   46 |   0

Abstract

We propose clustering samples given their pairwise similarities by factorizing the similarity matrix into the product of a cluster probability matrix and its transpose. We propose a rotation-based algorithm to compute this left-stochastic decomposition (LSD). Theoretical results link the LSD clustering method to a soft kernel k-means clustering, give conditions for when the factorization and clustering are unique, and provide error bounds. Experimental results on simulated and real similarity datasets show that the proposed method reliably provides accurate clusterings.

上一篇:Unsupervised Models of Images by Spike-and-Slab RBMs

下一篇:Time Series Clustering: Complex is Simpler!

用户评价
全部评价

热门资源

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • dynamical system ...

    allows to preform manipulations of heavy or bul...

  • The Variational S...

    Unlike traditional images which do not offer in...