-
New preprint
Layerwise Error Attribution for Fast and Robust Mixed-Precision Post-Training Quantization, S. Houache, Y. Traonmilin, J.-F. Aujol Abstract : 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 difficulties are to overcome the combinatorial nature of the allocation problem…
-
Best paper award ! (highlight talk)
Our paper From sparse recovery to plug-and-play priors, understanding trade-offs for stable recovery with generalized projected gradient descent, (A. Joundi, Y. Traonmilin, J.-F. Aujol) won one of the best papers award (highlight talk) of the Conference on Parsimony and Learning, 2026. Congrats everyone !
-
3 Papers accepted !
We just had the following papers accepted ! Congrats to everyone especially Phd students (S. Houache and A; Joundi) From sparse recovery to plug-and-play priors, understanding trade-offs for stable recovery with generalized projected gradient descent, A. Joundi, Y. Traonmilin, J.-F. Aujol, Accepted to Conference on Parsimony and Learning, 2026. A Recovery Theory for Diffusion Priors:…
-
New preprint
We uploaded the preprint Stochastic Orthogonal Regularization for deep projective priors, A. Joundi, Y. Traonmilin, A. Newson, 2025. abstract: “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 problems. In this paper, we focus on…
-
New preprint
We uploaded “On the impact of the parametrization of deep convolutional neural networks on post-training quantization“, S. Houache, J.-F. Aujol, Y.T. This paper introduces novel theoretical approximation bounds for the output of quantized neural networks, with a focus on convolutional neural networks (CNN). By considering layerwise parametrization and focusing on the quantization of weights, we…
-
New PhD
Congrats Dr Antoine Guennec who defended is PhD thesis yesterday on “Sparse models and deep priors for image decomposition into structure and texture”. He gave very nice contributions with modern methods on a challenging ill-posed problem. antoineguennec.perso.math.cnrs.fr
Yann Traonmilin
I am a CNRS researcher in the IOP team of the Institut de Mathématiques de Bordeaux.