Plug-and-Play Methods Provably Converge Even with Improperly Trained Denoisers: Convergence by Architectural Design

arXiv:2609.33087 · math.OC, eess.SP, stat.ML · Submitted 2026-09-27 · Read on arXiv

math.OC, eess.SP, stat.ML

Submitted: 2026-09-27

Updated: 2026-09-27

Terminology

Fidelity — 15× in this paper · explained in 2 episodes
Inverse Problem — 13× in this paper · explained in 2 episodes
Gradient Descent — 11× in this paper
Learned Proximal Network — 9× in this paper
Regularization — 9× in this paper · explained in 3 episodes
Convergence Guarantees — 8× in this paper · explained in 3 episodes
Proximal Gradient Descent — 8× in this paper
Activation Function — 6× in this paper · explained in 1 episode
Computed Tomography — 6× in this paper
Input Convex Neural Network — 4× in this paper
Alternating Direction Method of Multipliers (ADMM) — 2× in this paper · explained in 2 episodes
Sparsity — 2× in this paper · explained in 4 episodes
Total Variation — 2× in this paper
Accuracy — 1× in this paper · explained in 1 episode
Adam — 1× in this paper · explained in 2 episodes
Alignment — 1× in this paper · explained in 1 episode
Calibration — 1× in this paper · explained in 7 episodes
Flow Matching — 1× in this paper · explained in 7 episodes
Generalization — 1× in this paper · explained in 13 episodes
Gradient Flow — 1× in this paper · explained in 2 episodes
Loss Function — 1× in this paper · explained in 2 episodes
Magnetic Resonance Imaging — 1× in this paper
Objective Function — 1× in this paper · explained in 2 episodes