Estimating network edge probabilities by neighborhood smoothing

来源 :上海交通大学 | 被引量 : 0次 | 上传用户:alanyu97
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
  The problem of estimating probabilities of network edges from the observed adjacency matrix has important applications to predicting missing links and network denoising.
其他文献
Multi-state models have been widely used in assessing the dynamic disease progression under investigation.In some scenarios,a fraction of the population may be risk free for disease pro-gression.
Covariate-adjusted response-adaptive(CARA)designs use the available responses to skew the treatment allocation proportions in a clinical trial in favour of the treatment found best,thus far,for a give
We investigate the use of permutation tests for the analysis of cluster randomized trials,both in terms of parallel designs and stepped wedge designs.
Clustering is one of the first tools to explore big data.Classical techniques,such as hierarchical clustering and k-means,are usually based on the closeness between two data points or between a data p
This paper reviews the method of tail functions(TFs)for confidence estimation,starting with a seminal paper in the Canadian Journal of Statistics in 2006,and provides additional examples.
This work is motivated by the recent Korean MERS outbreak.We propose an easy adaptive estimation procedure for the case fatality rate(CFR)-the proportion of deaths among the cases during the course of
The probability of technical success(PTS)is a common measure in portfolio evaluation.
To include China in the global drug development and to have earlier regulatory approval of innovative drugs to benefit Chinese patients has become increasingly important.
We discuss the development of an unsupervised learning algorithm to cluster categorical data with sparse features.
We propose a flexible robust functional regression model,using various heavy-tailed processes,including a Student t-process.