報告題目：Convergent plug-and-play splitting methods for nonconvex learning-based optimization with applications
報 告 人：吳中明 副教授 南京信息工程大學
報告時間：2024年4月22日下午 03：30
報告地點：數學樓第二報告廳
校内聯系人：李欣欣 xinxinli@jlu.edu.cn
報告摘要：This talk will introduce several splitting methods for nonconvex optimization problems, and then combine them with extrapolation and Plug-and-Play (PnP) prior. Specifically, we investigate the convergence properties and applications of the three-operator splitting method, also known as Davis-Yin splitting (DYS) method, integrated with extrapolation and Plug-and-Play (PnP) denoiser within a nonconvex framework. Our approach provides an algorithmic framework that encompasses both extrapolated forward-backward splitting and extrapolated Douglas-Rachford splitting methods. To establish the convergence of the proposed method, we rigorously analyze its behavior based on the Kurdyka-Łojasiewicz property, subject to some tight parameter conditions. Moreover, we introduce two extrapolated PnP-DYS methods with convergence guarantee, where the traditional regularization prior is replaced by a gradient step-based denoiser. Finally, we conduct extensive experiments on image deblurring and image super-resolution problems, where our results showcase the advantage of the extrapolation strategy and the superior performance of the learning-based model that incorporates the PnP denoiser in terms of achieving high-quality recovery images.
報告人簡介：吳中明，南京信息工程大學副教授，香港中文大學博士後，新加坡國立大學訪問學者。研究方向為最優化理論、方法及其應用。在SIAM Journal on Imaging Sciences, IEEE Transactions on Signal Processing, Computational Optimization and Applications, Journal of Global Optimization, Mathematics of Computation, Annals of Operations Research等期刊發表/錄用論文三十餘篇。入選南京信息工程大學“青年科技之星”，江蘇省“雙創博士”，人社部博管辦“香江學者計劃”。擔任中國運籌學會宣傳工作委員會委員，中國運籌學會數學規劃分會青年理事，江蘇省運籌學會理事、副秘書長。主持國家自然科學青年基金項目，中國博士後面上資助項目，江蘇省科技智庫青年項目。
