Paper detail

Sharp MSE Bounds for Proximal Denoising

Denoising has to do with estimating a signal $x_0$ from its noisy observations $y=x_0+z$. In this paper, we focus on the "structured denoising problem", where the signal $x_0$ possesses a certain structure and $z$ has independent normally distributed entries with mean zero and variance $σ^2$. We employ a structure-inducing convex function $f(\cdot)$ and solve $\min_x\{\frac{1}{2}\|y-x\|_2^2+σλf(x)\}$ to estimate $x_0$, for some $λ>0$. Common choices for $f(\cdot)$ include the $\ell_1$ norm for sparse vectors, the $\ell_1-\ell_2$ norm for block-sparse signals and the nuclear norm for low-rank matrices. The metric we use to evaluate the performance of an estimate $x^*$ is the normalized mean-squared-error $\text{NMSE}(σ)=\frac{\mathbb{E}\|x^*-x_0\|_2^2}{σ^2}$. We show that NMSE is maximized as $σ\rightarrow 0$ and we find the \emph{exact} worst case NMSE, which has a simple geometric interpretation: the mean-squared-distance of a standard normal vector to the $λ$-scaled subdifferential $λ\partial f(x_0)$. When $λ$ is optimally tuned to minimize the worst-case NMSE, our results can be related to the constrained denoising problem $\min_{f(x)\leq f(x_0)}\{\|y-x\|_2\}$. The paper also connects these results to the generalized LASSO problem, in which, one solves $\min_{f(x)\leq f(x_0)}\{\|y-Ax\|_2\}$ to estimate $x_0$ from noisy linear observations $y=Ax_0+z$. We show that certain properties of the LASSO problem are closely related to the denoising problem. In particular, we characterize the normalized LASSO cost and show that it exhibits a "phase transition" as a function of number of observations. Our results are significant in two ways. First, we find a simple formula for the performance of a general convex estimator. Secondly, we establish a connection between the denoising and linear inverse problems.