Simple error bounds for regularized noisy linear inverse problems

Consider estimating a structured signal x
₀
from linear, underdetermined and noisy measurements y = Ax
₀
+z, via solving a variant of the lasso algorithm: x̂ = arg min
_x
{∥y-Ax∥2+λf(x)}. Here, f is a convex function aiming to promote the structure of x
₀
, say ℓ
₁
-norm to promote sparsity or nuclear norm to promote low-rankness. We assume that the entries of A are independent and normally distributed and make no assumptions on the noise vector z, other than it being independent of A. Under this generic setup, we derive a general, non-asymptotic and rather tight upper bound on the ℓ
₂
-norm of the estimation error ∥x̂ - x
₀
∥2. Our bound is geometric in nature and obeys a simple formula; the roles of λ, f and x
₀
are all captured by a single summary parameter δ(λ∂f(x
₀
)), termed the Gaussian squared distance to the scaled subdifferential. We connect our result to the literature and verify its validity through simulations.