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 1111.1041cs.ITmath.ITmath.STstat.TH
收藏

通过Minimax去噪实现压缩感知中相变的精确预测

Accurate Prediction of Phase Transitions in Compressed Sensing via a Connection to Minimax Denoising

David Donoho, Iain Johnstone, Andrea Montanari

摘要:

压缩感知假设,在一定范围内,人们可以对稀疏信号进行欠采样,但仍能准确地重建它。了解这种欠采样的精确限制对于理论和实践都很重要。我们提出了一个公式,广义稀疏对象的特征允许欠采样。该公式适用于压缩感知的近似消息传递(AMP)算法,在这里推广到采用除传统的标量软阈值去噪算子。本文给出了几个例子,包括标量降噪不来自凸惩罚-公司收缩非线性和极大极小非线性-和非标量降噪-块阈值,单调回归,总变差最小化。令变量eps = k/N和delta = n/N表示用于根据y=Ax_0对k-广义稀疏N-向量x_0进行采样的广义稀疏度和欠采样分数。这里A是n \times N测量矩阵,其条目是iid标准高斯。该公式指出,区分AMP对x_0的成功重建与不成功重建的相变曲线delta = delta(eps)由下式给出:|降噪器),其中M(eps| Denoiser)表示直接观察问题y = x + z中指定的最佳调谐去噪器的每坐标最小最大均方误差(MSE)。简而言之,无噪声欠采样问题的相变与去噪问题中的极小极大MSE相同。

英文摘要:

Compressed sensing posits that, within limits, one can undersample a sparse signal and yet reconstruct it accurately. Knowing the precise limits to such undersampling is important both for theory and practice. We present a formula that characterizes the allowed undersampling of generalized sparse objects. The formula applies to Approximate Message Passing (AMP) algorithms for compressed sensing, which are here generalized to employ denoising operators besides the traditional scalar soft thresholding denoiser. This paper gives several examples including scalar denoisers not derived from convex penalization -- the firm shrinkage nonlinearity and the minimax nonlinearity -- and also nonscalar denoisers -- block thresholding, monotone regression, and total variation minimization. Let the variables eps = k/N and delta = n/N denote the generalized sparsity and undersampling fractions for sampling the k-generalized-sparse N-vector x_0 according to y=Ax_0. Here A is an n\times N measurement matrix whose entries are iid standard Gaussian. The formula states that the phase transition curve delta = delta(eps) separating successful from unsuccessful reconstruction of x_0 by AMP is given by: delta = M(eps| Denoiser), where M(eps| Denoiser) denotes the per-coordinate minimax mean squared error (MSE) of the specified, optimally-tuned denoiser in the directly observed problem y = x + z. In short, the phase transition of a noiseless undersampling problem is identical to the minimax MSE in a denoising problem.

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。

↑