Provably Convergent Plug-and-Play Quasi-Newton Methods for Imaging Inverse Problems

Add to your list(s) Download to your calendar using vCal

• Junqi Tang (University of Birmingham, School of Mathematics)
• Tuesday 13 June 2023, 14:00-15:00
• Venue to be confirmed.

If you have a question about this talk, please contact Sergey Sergeev.

Plug-and-Play (PnP) methods are a class of efficient iterative methods that aim to combine data fidelity terms and deep denoisers using classical optimization algorithms, such as ISTA or ADMM . Existing provable PnP methods impose heavy restrictions on the denoiser or fidelity function, such as nonexpansiveness or strict convexity. In this work, we propose a provable PnP method that imposes relatively light conditions based on proximal denoisers, and introduce a quasi-Newton step to greatly accelerate convergence. By specially parameterizing the deep denoiser as a gradient step, we further characterize the fixed-points of the quasi-Newton PnP algorithm. We demonstrate the effectiveness of our scheme in applications such as image deblurring, inpainting and superresolution, observing order-of-magnitude acceleration over state-of-the-art PnP algorithms.

This talk is part of the Optimisation and Numerical Analysis Seminars series.

This talk is included in these lists:

• Optimisation and Numerical Analysis Seminars
• School of Mathematics events
• Venue to be confirmed

Note that ex-directory lists are not shown.