18–20 mai 2026
Bordeaux
Fuseau horaire Europe/Paris

Dualization of Plug-and-Play

Non programmé
25m
Salle de Conférences (Bordeaux)

Salle de Conférences

Bordeaux

351 Cours de la Libération, 33400 Talence, France

Orateur

M. Guido Samuel Tapia Riera (IMB)

Description

We present a new algorithm for minmax optimization problems of the form
$\min_x \max_y \; \phi(x,y) - h(y)$, where $\phi$ has block-wise Lipschitz-continuous gradient,
semi-convex in $x$, concave in $y$ and either $\phi$ or $-h$ is strongly concave in $y$.
Such problems arise in image inverse problems where $\phi$ encodes regularity prior on the image to restore $x$.

State-of-the-art optimization methods for such problems rely on alternate explicit gradient descent-ascent
steps on the coupling term $\phi$. On the other hand, Plug and Play (PnP) approaches replace the explicit
gradient step on $\phi$ by a neural network that is at the same time an image denoiser, and a proximal operator
of a semi-convex potential. This proximal step does not fit into the current optimization framework for which
convergence is known to hold.

In this context, we here propose a new min-max optimization scheme with proximal steps on $x$, thus allowing
to provide convergence guarantees for some PnP applications. We derive sufficient conditions on the convergence
of the algorithm and showcase its interest for PnP image restoration.

Documents de présentation

Aucun document.