{"ID":2873984,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.05736","arxiv_id":"2509.05736","title":"Stabilizing RED using the Koopman Operator","abstract":"The widely used RED (Regularization-by-Denoising) framework uses pretrained denoisers as implicit regularizers for model-based reconstruction. Although RED generally yields high-fidelity reconstructions, the use of black-box denoisers can sometimes lead to instability. In this letter, we propose a data-driven mechanism to stabilize RED using the Koopman operator, a classical tool for analyzing dynamical systems. Specifically, we use the operator to capture the local dynamics of RED in a low-dimensional feature space, and its spectral radius is used to detect instability and formulate an adaptive step-size rule that is model-agnostic, has modest overhead, and requires no retraining. We test this with several pretrained denoisers to demonstrate the effectiveness of the proposed Koopman stabilization.","short_abstract":"The widely used RED (Regularization-by-Denoising) framework uses pretrained denoisers as implicit regularizers for model-based reconstruction. Although RED generally yields high-fidelity reconstructions, the use of black-box denoisers can sometimes lead to instability. In this letter, we propose a data-driven mechanism...","url_abs":"https://arxiv.org/abs/2509.05736","url_pdf":"https://arxiv.org/pdf/2509.05736v1","authors":"[\"Shraddha Chavan\",\"Kunal N. Chaudhury\"]","published":"2025-09-06T14:58:02Z","proceeding":"eess.IV","tasks":"[\"eess.IV\"]","methods":"[]","has_code":false}