Publications

You can also check my publications directly on HAL  or  Google scholar. 

Errata:

You can find an errata at the end of this page for articles marked by a *.

Preprint:

Adaptive Parameter Selection For Gradient-sparse + Low Patch-rank Recovery: Application To Image Decomposition. A. Guennec, J.-F. Aujol, Y. Traonmilin. EUSIPCO 2024. (EFFIREG)

A theory of optimal convex regularization for low-dimensional recovery, Y. Traonmilin, R. Gribonval and S. Vaiter, to appear in Information and Inference, 2024.  (EFFIREG)

Estimation of off-the-grid sparse spikes with over-parametrized projected gradient descent: theory and application. P.-J. Bénard, Y. Traonmilin, J.-F. Aujol and E. Soubies, Inverse Problems, 2023. The final publication is available at https://iopscience.iop.org/article/10.1088/1361-6420/ad33e4  (EFFIREG)

Batch-less stochastic gradient descent for compressive learning of deep regularization for image denoising, H. Shi, Y. Traonmilin and J.-F. Aujol, JMIV, 2023. The final publication is available at https://rdcu.be/dA89t .(EFFIREG)

On strong basins of attractions for non-convex sparse spike estimation: upper and lower bounds, Y. Traonmilin, J.F. Aujol, A. Leclaire and P.J. Bénard.  JMIV, 2023. The final publication is available at https://rdcu.be/dnjmu . (EFFIREG).

Compressive learning of deep regularization for denoising, H. Shi, Y. Traonmilin, J.-F. Aujol, SSVM 2023. (EFFIREG)

Piecewise linear prediction model for action tracking in sports, A. Baldanza, J.F. Aujol, Y. Traonmilin and F. Alary, EUSIPCO, 2022.

Fast off-the-grid sparse recovery with over-parametrized projected gradient descent, P.J. Bénard, Y. Traonmilin and J.F. Aujol, EUSIPCO 2022. (EFFIREG)

Compressive learning for patch-based image denoising, H. Shi, Y. Traonmilin and J-F. Aujol, SIAM Journal on Imaging Sciences, 2022. (EFFIREG)

The basins of attraction of the global minimizers of non-convex inverse problems with low-dimensional models in infinite dimension, Y. Traonmilin, J.-F. Aujol and A. Leclaire, Information and Inference, 2022. (EFFIREG)

Sur la performance des méthodes convexes et non-convexes de reconstruction de modèles de faible dimension en science des données, Y. Traonmilin, Habilitation à diriger des recherches, 2021.

Découpage automatique de vidéos de sport amateur par détection de personnes et analyse de contenu colorimétrique, A. Baldanza, J.-F. Aujol, Y. Traonmilin and F. Alary, ORASIS 2021.

Sketched learning for image denoising, H. Shi, Y. Traonmilin and J-F. Aujol, Scale Space and Variational Methods in Computer Vision, 2021. (EFFIREG)

Statistical Learning Guarantees for Compressive Clustering and Compressive Mixture Modeling. R. Gribonval, G. Blanchard, N. Keriven  and Y. Traonmilin, To appear in Mathematical Statistics and Learning,  2021.

Compressive Statistical Learning with Random Feature Moments. R. Gribonval, G. Blanchard, N. Keriven  and Y. Traonmilin, To appear in Mathematical Statistics and Learning, 2021.

Projected gradient descent for non-convex sparse spike estimation, IEEE Signal Processing Letters,  Y. Traonmilin, J.-F. Aujol and Arthur Leclaire, 2020.

« The basins of attraction of the global minimizers of the non-convex sparse spikes estimation problem », Y. Traonmilin and J.-F. Aujol, Inverse Problems, 2019.*

Is the 1-norm the best convex sparse regularization?, Y.  Traonmilin, S. Vaiter and R. Gribonval, iTWIST’18, 2018.

Optimality of 1-norm regularization among weighted 1-norms for sparse recovery: a case study on how to find optimal regularizations. Y. Traonmilin and S. Vaiter, NCMIP, 2018.

Stable recovery of low-dimensional cones in Hilbert spaces: One RIP to rule them all. Applied and Computational Harmonic Analysis, Y. Traonmilin and R. Gribonval, 2018.*

Compressed sensing in Hilbert spaces.  Y. Traonmilin, G. Puy, R. Gribonval and M. E. Davies, Compressed Sensing and Its Applications, (Book chapter), 2017.

Compressive K-means. N. Keriven, N. Tremblay, Y. Traonmilin and R. Gribonval, ICASSP, 2017.

Phase Unmixing : Multichannel Source Separation with Magnitude Constraints. A. Deleforge and Y. Traonmilin, ICASSP, 2017.

A framework for low-complexity signal recovery and its application to structured sparsity. Y. Traonmilin and R. Gribonval, 2016 IEEE Information Theory Workshop (ITW), Cambridge, pp. 156-160,   2016.

Robust Multi-image Processing With Optimal Sparse Regularization. Y. Traonmilin, S. Ladjal, and A. Almansa, JMIV, 2014. The final
publication is available at http://www.springerlink.com/openurl.asp?genre=article&id=doi:10.1007/s10851-014-0532-1.

Relations entre le modèle d’image et le nombre de mesures pour une super-résolution fidèle, Y. Traonmilin, PhD THesis, 2014

Simultaneous High Dynamic Range and Super-Resolution Imaging Without Regularization.
Y. Traonmilin and C. Aguerrebere, SIIMS, 2013.

Quantification de la robustesse de la super-résolution par minimisation L1
Y. Traonmilin, S. Ladjal, and A. Almansa,
23ème Colloque Gretsi (Gretsi 2013), Brest : France (2013).

Outlier removal power of the L1-Norm Super-Resolution.
Y. Traonmilin, Saïd Ladjal, and Andrés Almansa.
Scale Space and Variational Methods in Computer Vision, volume 7893 of Lecture Notes in Computer Science.

On the amount of regularization for super-resolution reconstruction.
Y. Traonmilin, Saïd Ladjal, and Andrés Almansa, Technical report, 2012.

On the amount of regularization for Super-Resolution interpolation.
Y. Traonmilin, Saïd Ladjal, and Andrés Almansa.
In 20th European Signal Processing Conference 2012 (EUSIPCO 2012), Bucharest, Romania, August 2012.

Previous work (Geophysical signal processing, main author)

Statics-preserving projection filtering.
Y. Traonmilin and N. Gulunay. Geophysical Prospecting, 2012.

Statics preserving projection filtering.
Y. Traonmilin and N. Gulunay. SEG Technical Program Expanded Abstracts, 30(1):3638–3642, 2011.

Multi-dip estimation in n dimensions.
Y. Traonmilin, G. Lambaré, P. Herrmann, N. Deladerriere and K. Garceran. 71st EAGE Conference & Exhibition, 2009.

Structurally consistent f-x filtering.
Y. Traonmilin and P. Herrmann. SEG Technical Program Expanded Abstracts, 27(1):2642–2646, 2008.

*For : The basins of attraction of the global minimizers of the non-convex sparse spikes estimation problem

In equation (32), on the right side you should read ||x||^2 instead of ||Ax||^2.

In “Proof of Corollary3.1.” the stability of iterates is deduced from the co-coercivity of g around the global minimizer (instead of a nonexpensiveness argument). This stability can be proved generally (see The basins of attraction of the global minimizers of non-convex inverse problems with low-dimensional models in infinite dimension,)

*For : Stable recovery of low-dimensional cones in Hilbert spaces: One RIP to rule them all.

In Fact 2.1. You should read A⊂S(1) instead of A⊂B(1)