12 papers
Layerwise Error Attribution for Fast and Robust Mixed-Precision Post-Training Quantization
Samy Houache, Yann Traonmilin, Jean-François Aujol
Mixed-precision post-training quantization is a network compression method that assigns bits layer by layer, under a global memory budget using a small calibration set. The main di…
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…
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…
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…
Parameter-free structure-texture image decomposition by unrolling
Laura Girometti, Jean-François Aujol, Antoine Guennec +1
In this work, we propose a parameter-free and efficient method to tackle the structure-texture image decomposition problem. In particular, we present a neural network LPR-NET based…
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…
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…
Projected Block Coordinate Descent for sparse spike estimation
Pierre-Jean Bénard, Yann Traonmilin, Jean François Aujol
We consider the problem of recovering off-the-grid spikes from linear measurements. The state of the art Over-Parametrized Continuous Orthogonal Matching Pursuit (OP-COMP) with Pro…
Batch-less stochastic gradient descent for compressive learning of deep regularization for image denoising
Hui Shi, Yann Traonmilin, J-F Aujol
We consider the problem of denoising with the help of prior information taken from a database of clean signals or images. Denoising with variational methods is very efficient if a…
Fast off-the-grid sparse recovery with over-parametrized projected gradient descent
Pierre-Jean Bénard, Yann Traonmilin, Jean-François Aujol
We consider the problem of recovering off-the-grid spikes from Fourier measurements. Successful methods such as sliding Frank-Wolfe and continuous orthogonal matching pursuit (OMP)…
A theory of optimal convex regularization for low-dimensional recovery
Yann Traonmilin, Rémi Gribonval, Samuel Vaiter
We consider the problem of recovering elements of a low-dimensional model from under-determined linear measurements. To perform recovery, we consider the minimization of a convex r…