How robust is randomized blind deconvolution via nuclear norm minimization against adversarial noise?
This work provides theoretical insights into the robustness of nuclear norm minimization for blind deconvolution, which is incremental as it builds on existing low-rank recovery frameworks to better explain empirical evidence.
The paper tackles the problem of blind deconvolution with adversarial noise, developing improved recovery guarantees that show square-root scaling in the noise level, addressing limitations of prior bounds with large dimension factors.
In this paper, we study the problem of recovering two unknown signals from their convolution, which is commonly referred to as blind deconvolution. Reformulation of blind deconvolution as a low-rank recovery problem has led to multiple theoretical recovery guarantees in the past decade due to the success of the nuclear norm minimization heuristic. In particular, in the absence of noise, exact recovery has been established for sufficiently incoherent signals contained in lower-dimensional subspaces. However, if the convolution is corrupted by additive bounded noise, the stability of the recovery problem remains much less understood. In particular, existing reconstruction bounds involve large dimension factors and therefore fail to explain the empirical evidence for dimension-independent robustness of nuclear norm minimization. Recently, theoretical evidence has emerged for ill-posed behavior of low-rank matrix recovery for sufficiently small noise levels. In this work, we develop improved recovery guarantees for blind deconvolution with adversarial noise which exhibit square-root scaling in the noise level. Hence, our results are consistent with existing counterexamples which speak against linear scaling in the noise level as demonstrated for related low-rank matrix recovery problems.