You KAN Do It in a Single Shot:
Plug-and-Play Methods with Single-Instance Priors


Yanqi Cheng
Carola-Bibiane Schönlieb
Angelica I. Aviles-Rivero

affiliations


The visualisation of our proposed framework.
This is a website made for You KAN Do It in a Single Shot: Plug-and-Play Methods with Single-Instance Priors.

Abstract

The use of Plug-and-Play (PnP) methods has become a central approach for solving inverse problems, with denoisers serving as regularising priors that guide optimisation towards a clean solution. In this work, we introduce KAN-PnP, an optimisation framework that incorporates Kolmogorov-Arnold Networks (KANs) as denoisers within the Plug-and-Play (PnP) paradigm. KAN-PnP is specifically designed to solve inverse problems with single-instance priors, where only a sin- gle noisy observation is available, eliminating the need for large datasets typically required by traditional denoising methods. We show that KANs, based on the Kolmogorov-Arnold representation theorem, serve effectively as priors in such set- tings, providing a robust approach to denoising. We prove that the KAN denoiser is Lipschitz continuous, ensuring stability and convergence in optimisation algo- rithms like PnP-ADMM, even in the context of single-shot learning. Additionally, we provide theoretical guarantees for KAN-PnP, demonstrating its convergence under key conditions: the convexity of the data fidelity term, Lipschitz continuity of the denoiser, and boundedness of the regularisation functional. These condi- tions are crucial for stable and reliable optimisation. Our experimental results show, on super-resolution and joint optimisation, that KAN-PnP outperforms exiting methods, delivering superior performance in single-shot learning with min- imal data. The method exhibits strong convergence properties, achieving high accuracy with fewer iterations.


Paper and Supplementary Material


Yanqi Cheng, Carola-Bibiane Schönlieb, Angelica I Aviles-Rivero.
You KAN Do It in a Single Shot: Plug-and-Play Methods with Single-Instance Priors


[arXiv]   [Bibtex]



Acknowledgements

YC is funded by an AstraZeneca studentship and a Google studentship. CBS acknowl- edges support from the Philip Leverhulme Prize, the Royal Society Wolfson Fellowship, the EPSRC advanced career fellowship EP/V029428/1, EPSRC grants EP/S026045/1 and EP/T003553/1, EP/N014588/1, EP/T017961/1, the Wellcome Innovator Awards 215733/Z/19/Z and 221633/Z/20/Z, the European Union Horizon 2020 research and innovation programme under the Marie Skodowska-Curie grant agreement No. 777826 NoMADS, the Cantab Capital Institute for the Mathematics of Information and the Alan Turing Institute. AIAR gratefully acknowledges the support from Yau Mathematical Sciences Center, Tsinghua University.