...
首页> 外文期刊>IEEE Transactions on Information Theory >Lossy Compression via Sparse Linear Regression: Performance Under Minimum-Distance Encoding
【24h】

Lossy Compression via Sparse Linear Regression: Performance Under Minimum-Distance Encoding

机译:通过稀疏线性回归进行有损压缩:最小距离编码下的性能

获取原文
获取原文并翻译 | 示例
           

摘要

We study a new class of codes for lossy compression with the squared-error distortion criterion, designed using the statistical framework of high-dimensional linear regression. Codewords are linear combinations of subsets of columns of a design matrix. Called a sparse superposition or sparse regression codebook, this structure is motivated by an analogous construction proposed recently by Barron and Joseph for communication over an Additive White Gaussian Noise channel. For independent identically distributed (i.i.d) Gaussian sources and minimum-distance encoding, we show that such a code can attain the Shannon rate-distortion function with the optimal error exponent, for all distortions below a specified value. It is also shown that sparse regression codes are robust in the following sense: a codebook designed to compress an i.i.d Gaussian source of variance $sigma^{2}$ with (squared-error) distortion $D$ can compress any ergodic source of variance less than $sigma^{2}$ to within distortion $D$ . Thus, the sparse regression ensemble retains many of the good covering properties of the i.i.d random Gaussian ensemble, while having a compact representation in terms of a matrix whose size is a low-order polynomial in the block-length.
机译:我们使用平方误差失真准则研究一类新的有损压缩代码,该准则是使用高维线性回归的统计框架设计的。码字是设计矩阵的列子集的线性组合。这种结构被称为稀疏叠加或稀疏回归代码本,其结构是由Barron和Joseph提出的一种类似结构所激发的,该结构用于通过加性高斯白噪声信道进行通信。对于独立的均匀分布(i.d.d)高斯源和最小距离编码,我们表明对于所有低于指定值的失真,这样的代码都可以达到具有最佳误差指数的香农率失真函数。还显示出稀疏回归代码在以下方面具有鲁棒性:设计用于压缩iid高斯方差源$ sigma ^ {2} $并具有(平方误差)失真$ D $的码本可以压缩任何遍历方差源小于$ sigma ^ {2} $到失真$ D $之内。因此,稀疏回归系保留了i.i.d随机高斯系的许多良好的覆盖特性,同时具有矩阵的紧凑表示,该矩阵的大小是块长的低阶多项式。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号