Classification and reconstruction of compressed GMM signals with side information
Classification and reconstruction of compressed GMM signals with side information
复制标题
具有辅助信息的压缩 GMM 信号的分类和重构
DOI：
10.1109/isit.2015.7282604
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
M. Rodrigues
中科院分区：
文献类型：
--
作者：
F. Renna;Liming Wang;Xin Yuan;Jianbo Yang;G. Reeves;Robert Calderbank;L. Carin;M. Rodrigues
本文提供了一个表征的性能限制的分类和重建的高维信号从嘈杂的压缩测量，在边信息的存在。我们假设感兴趣的信号和边信息信号是从分布/分量的相关混合中提取的，其中与特定类别标签相关联的每个分量遵循高斯混合模型（GMM）。我们提供了尖锐的充分和/或必要条件的相变的误分类概率和重建误差在低噪声制度。这些条件使人联想到众所周知的Slepian-Wolf和Wyner-Ziv条件，它们是从感兴趣的信号获得的测量的数量、从边信息信号获得的测量的数量以及这些信号的几何形状和它们的相互作用的函数。
This paper offers a characterization of performance limits for classification and reconstruction of high-dimensional signals from noisy compressive measurements, in the presence of side information. We assume the signal of interest and the side information signal are drawn from a correlated mixture of distributions/components, where each component associated with a specific class label follows a Gaussian mixture model (GMM). We provide sharp sufficient and/or necessary conditions for the phase transition of the misclassification probability and the reconstruction error in the low-noise regime. These conditions, which are reminiscent of the well-known Slepian-Wolf and Wyner-Ziv conditions, are a function of the number of measurements taken from the signal of interest, the number of measurements taken from the side information signal, and the geometry of these signals and their interplay.
影响因子：
3.8
作者：
Chen, Guang-Hong;Tang, Jie;Leng, Shuai
通讯作者：
Leng, Shuai