8 papers
A note on the convergence of RED algorithms under minimal hypotheses and open questions
Yann Traonmilin, J. -F Aujol
In this note, we give a convergence result for a modified ''regularization-by-denoising''(RED) algorithm under a restricted isometry condition on measurements and a restricted Lips…
From sparse recovery to plug-and-play priors, understanding trade-offs for stable recovery with generalized projected gradient descent
Ali Joundi, Yann Traonmilin, Jean-François Aujol
We consider the problem of recovering an unknown low-dimensional vector from noisy, underdetermined observations. We focus on the Generalized Projected Gradient Descent (GPGD) fram…
Stochastic Orthogonal Regularization for deep projective priors
Ali Joundi, Yann Traonmilin, Alasdair Newson
Many crucial tasks of image processing and computer vision are formulated as inverse problems. Thus, it is of great importance to design fast and robust algorithms to solve these p…
On the impact of the parametrization of deep convolutional neural networks on post-training quantization
Samy Houache, Jean François Aujol, Yann Traonmilin
This paper introduces novel theoretical approximation bounds for the output of quantized neural networks, with a focus on convolutional neural networks (CNN). By considering layerw…
A Recovery Theory for Diffusion Priors: Deterministic Analysis of the Implicit Prior Algorithm
Oscar Leong, Yann Traonmilin
Recovering high-dimensional signals from corrupted measurements is a central challenge in inverse problems. Recent advances in generative diffusion models have shown remarkable emp…
Towards optimal algorithms for the recovery of low-dimensional models with linear rates
Yann Traonmilin, Jean François Aujol, Antoine Guennec
We consider the problem of recovering elements of a low-dimensional model from linear measurements. From signal and image processing to inverse problems in data science, this quest…