arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1401.6578math.OCcs.ITmath.ITmath.STstat.TH
收藏

正则化噪声线性反问题的简单误差界

Simple Error Bounds for Regularized Noisy Linear Inverse Problems

Christos Thrampoulidis, Samet Oymak, Babak Hassibi

摘要:

考虑通过求解套索算法的变型:$\hat{\mathbf{x}}=\arg\min_\mathbf{x}\{ \|\mathbf{y}-\mathbf{A}\mathbf{x}\|_2+λf(\mathbf{x})\}$,从线性、欠定和噪声测量$\mathbf{y}=\mathbf{A}\mathbf{x}_0+\mathbf{z}$估计结构化信号$\mathbf{x}_0$。这里,$f$是旨在提升$\mathbf{x}_0$的结构的凸函数,例如提升稀疏性的$\ell_1$ -范数或提升低秩性的核范数。我们假设$\mathbf{A}$的条目是独立的并且是正态分布的,并且对噪声向量$\mathbf{z}$不做任何假设,除了它独立于$\mathbf{A}$之外。在这种通用的设置下,我们推导出一个一般的,非渐近的和相当紧的估计误差$\|\hat{\mathbf{x}}-\mathbf{x}_0\|_2$的$\ell_2$ -范数上界。我们的界限本质上是几何的,并且遵循一个简单的公式; $λ$、$f$和$\mathbf{x}_0$的作用都由单个汇总参数$δ(λ\partial((f(\mathbf{x}_0)))$捕获,该参数称为到缩放次微分的高斯平方距离。我们将我们的结果连接到文献,并通过模拟验证其有效性。

英文摘要:

Consider estimating a structured signal $\mathbf{x}_0$ from linear, underdetermined and noisy measurements $\mathbf{y}=\mathbf{A}\mathbf{x}_0+\mathbf{z}$, via solving a variant of the lasso algorithm: $\hat{\mathbf{x}}=\arg\min_\mathbf{x}\{ \|\mathbf{y}-\mathbf{A}\mathbf{x}\|_2+λf(\mathbf{x})\}$. Here, $f$ is a convex function aiming to promote the structure of $\mathbf{x}_0$, say $\ell_1$-norm to promote sparsity or nuclear norm to promote low-rankness. We assume that the entries of $\mathbf{A}$ are independent and normally distributed and make no assumptions on the noise vector $\mathbf{z}$, other than it being independent of $\mathbf{A}$. Under this generic setup, we derive a general, non-asymptotic and rather tight upper bound on the $\ell_2$-norm of the estimation error $\|\hat{\mathbf{x}}-\mathbf{x}_0\|_2$. Our bound is geometric in nature and obeys a simple formula; the roles of $λ$, $f$ and $\mathbf{x}_0$ are all captured by a single summary parameter $δ(λ\partial((f(\mathbf{x}_0)))$, termed the Gaussian squared distance to the scaled subdifferential. We connect our result to the literature and verify its validity through simulations.

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。

↑