Scalable Plug-and-Play ADMM with Convergence Guarantees
This work addresses scalability issues for researchers and practitioners in imaging and inverse problems, though it is incremental as it builds on existing PnP-ADMM methods.
The paper tackled the impracticality of plug-and-play priors (PnP) algorithms in large-scale settings due to high computational and memory demands by proposing an incremental variant of PnP-ADMM, achieving scalability with fast convergence and theoretical guarantees.
Plug-and-play priors (PnP) is a broadly applicable methodology for solving inverse problems by exploiting statistical priors specified as denoisers. Recent work has reported the state-of-the-art performance of PnP algorithms using pre-trained deep neural nets as denoisers in a number of imaging applications. However, current PnP algorithms are impractical in large-scale settings due to their heavy computational and memory requirements. This work addresses this issue by proposing an incremental variant of the widely used PnP-ADMM algorithm, making it scalable to large-scale datasets. We theoretically analyze the convergence of the algorithm under a set of explicit assumptions, extending recent theoretical results in the area. Additionally, we show the effectiveness of our algorithm with nonsmooth data-fidelity terms and deep neural net priors, its fast convergence compared to existing PnP algorithms, and its scalability in terms of speed and memory.