arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.07971cs.ITcond-mat.dis-nncs.LGmath.ITmath.PR
收藏

稀疏尖峰矩阵估计中的全有或全无统计和计算相变

All-or-nothing statistical and computational phase transitions in sparse spiked matrix estimation

International Center for Theoretical Physics(国际理论物理中心);Ecole Polytechnique Fédérale de Lausanne(洛桑联邦理工学院);Columbia University(哥伦比亚大学)

Jean Barbier, Nicolas Macris, Cynthia Rush

摘要:

我们确定的统计和计算限制估计的秩一矩阵(尖峰)损坏的加性高斯噪声矩阵,在稀疏的限制,其中潜在的隐藏向量(构成秩一矩阵)有一些非零分量的规模与向量的总维度次线性,和信噪比趋于无穷大在适当的速度。我们证明了显式的低维变分公式的渐近互信息之间的尖峰和观察到的噪声矩阵和分析的近似消息传递算法在稀疏制度。对于Bernoulli和Bernoulli-Rademacher分布向量,当稀疏性和信号强度满足适当的比例关系时,我们发现渐近最小值和算法均方误差的全有或全无相变。这些跳从他们的最大可能值为零,在定义良好的信号噪声阈值的渐近值,我们确切地确定。在渐近制度的算法差距发散,稀疏恢复是很难近似消息传递。

英文摘要:

We determine statistical and computational limits for estimation of a rank-one matrix (the spike) corrupted by an additive gaussian noise matrix, in a sparse limit, where the underlying hidden vector (that constructs the rank-one matrix) has a number of non-zero components that scales sub-linearly with the total dimension of the vector, and the signal-to-noise ratio tends to infinity at an appropriate speed. We prove explicit low-dimensional variational formulas for the asymptotic mutual information between the spike and the observed noisy matrix and analyze the approximate message passing algorithm in the sparse regime. For Bernoulli and Bernoulli-Rademacher distributed vectors, and when the sparsity and signal strength satisfy an appropriate scaling relation, we find all-or-nothing phase transitions for the asymptotic minimum and algorithmic mean-square errors. These jump from their maximum possible value to zero, at well defined signal-to-noise thresholds whose asymptotic values we determine exactly. In the asymptotic regime the statistical-to-algorithmic gap diverges indicating that sparse recovery is hard for approximate message passing.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑