arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1004.1218math.STcs.ITmath.ITstat.TH
收藏

压缩感知中的噪声敏感度相变

The Noise-Sensitivity Phase Transition in Compressed Sensing

David L. Donoho, Arian Maleki, Andrea Montanari

摘要:

考虑线性方程的噪声欠定组:y= Ax 0 + z 0,其中n × N测量矩阵A,n < N,高斯白噪声z 0 ~ N(0,σ^2 I)。y和A都已知,x 0和z 0都未知,我们寻求x 0的近似值。当x 0有几个非零值时,通过l1-惩罚l2最小化获得有用的近似,其中重建\hxl求解min|| y轴||^2/2 + λ| |x||_1。通过均方误差(MSE = E)评估性能||\hxl - x0||_2^2/N)。考虑具有iid高斯元素和大系统极限的矩阵A,其中n,N \to \infty具有n/N \to δ和k/n \to ρ。将MSE/σ^2的比值称为噪声灵敏度。我们开发正式表达式的MSE的\hxl,并评估其最坏情况下的正式噪声灵敏度在所有类型的k-稀疏信号。曲线ρ= \rhoMSE(δ)将相空间0 < δ,ρ< 1分为两个区域。形式噪声灵敏度在整个区域ρ< \rhoMSE(δ)中是有界的,并且在整个区域ρ> \rhoMSE(δ)中是无界的。相位边界ρ= \rhoMSE(δ)与已知的k稀疏无噪声情况下l1 - l0最小化的等效相变曲线相同。因此,一个单一的相位边界描述了基本的相位过渡,无噪声和噪声的情况下。大量的计算实验验证了这种形式主义的预测,包括存在的博弈理论结构的基础it. Underlying我们的形式主义是AMP算法之前介绍的作者。作者的其他论文详细介绍了AMP的形式MSE的表达式及其与l1-惩罚重建的密切联系。在这里,我们推导出AMP的最小最大形式MSE,然后读出l1-惩罚重建的结果。

英文摘要:

Consider the noisy underdetermined system of linear equations: y=Ax0 + z0, with n x N measurement matrix A, n < N, and Gaussian white noise z0 ~ N(0,σ^2 I). Both y and A are known, both x0 and z0 are unknown, and we seek an approximation to x0. When x0 has few nonzeros, useful approximations are obtained by l1-penalized l2 minimization, in which the reconstruction \hxl solves min || y - Ax||^2/2 + λ||x||_1. Evaluate performance by mean-squared error (MSE = E ||\hxl - x0||_2^2/N). Consider matrices A with iid Gaussian entries and a large-system limit in which n,N\to\infty with n/N \to δand k/n \to ρ. Call the ratio MSE/σ^2 the noise sensitivity. We develop formal expressions for the MSE of \hxl, and evaluate its worst-case formal noise sensitivity over all types of k-sparse signals. The phase space 0 < δ, ρ< 1 is partitioned by curve ρ= \rhoMSE(δ) into two regions. Formal noise sensitivity is bounded throughout the region ρ< \rhoMSE(δ) and is unbounded throughout the region ρ> \rhoMSE(δ). The phase boundary ρ= \rhoMSE(δ) is identical to the previously-known phase transition curve for equivalence of l1 - l0 minimization in the k-sparse noiseless case. Hence a single phase boundary describes the fundamental phase transitions both for the noiseless and noisy cases. Extensive computational experiments validate the predictions of this formalism, including the existence of game theoretical structures underlying it. Underlying our formalism is the AMP algorithm introduced earlier by the authors. Other papers by the authors detail expressions for the formal MSE of AMP and its close connection to l1-penalized reconstruction. Here we derive the minimax formal MSE of AMP and then read out results for l1-penalized reconstruction.

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。

↑