资源分类
》 资源 》论文》Clustering with Bregman Divergences: an Asymptotic Analysis

Clustering with Bregman Divergences: an Asymptotic Analysis

2020-02-05 | |  52 |   48 |   0

Abstract

 Clustering, in particular k-means clustering, is a central topic in data analysis. Clustering with Bregman divergences is a recently proposed generalization of k-means clustering which has already been widely used in applications. In this paper we analyze theoretical properties of Bregman clustering when the number of the clusters k is large. We establish quantization rates and describe the limiting distribution of the centers as k image.png, extending well-known results for k-means clustering.

上一篇：Learning Tree Structured Potential Games

下一篇：Improved Techniques for Training GANs

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to learn...

    The move from hand-designed features to learned...

  • A Mathematical Mo...

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