{"id":10,"date":"2013-05-24T13:05:26","date_gmt":"2013-05-24T13:05:26","guid":{"rendered":"http:\/\/traonmilin.wp.mines-telecom.fr\/?page_id=10"},"modified":"2026-03-11T09:14:13","modified_gmt":"2026-03-11T09:14:13","slug":"publications","status":"publish","type":"page","link":"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/?page_id=10","title":{"rendered":"Publications"},"content":{"rendered":"\n

You can also check my publications directly on HAL<\/a>  or  Google scholar<\/a>. <\/p>\n\n\n\n

Errata:<\/h5>\n\n\n

You can find an errata at the end of this page for articles marked by a *.<\/p>\n

Preprint:<\/h3>\n
\n
\n
\n
\n

Towards optimal algorithms for the recovery of low-dimensional models with linear rates<\/a> , Y. Traonmilin , J.-F. Aujol, A. Guennec, 2025. (EFFIREG)<\/p>\n

Stochastic Orthogonal Regularization for deep projective priors<\/a>,\u00a0 A. Joundi, Y. Traonmilin, A. Newson, 2025. (EFFIREG)<\/p>\n<\/div>\n

Published:<\/h3>\n

A note on the convergence of RED algorithms under minimal hypotheses and open questions<\/a>, Y. Traonmilin, J.-F. Aujol, technical report, 2026.<\/p>\n

From sparse recovery to plug-and-play priors, understanding trade-offs for stable recovery with generalized projected gradient descent<\/a>, A. Joundi, Y. Traonmilin, J.-F. Aujol, Accepted to Conference on Parsimony and Learning,\u00a0 2026. Highlight talk<\/strong>.<\/p>\n

A Recovery Theory for Diffusion Priors: Deterministic Analysis of the Implicit Prior Algorithm<\/a>, O. Leong, Y. Traonmilin, accepted to AISTATS 2026.<\/p>\n

On the impact of the parametrization of deep convolutional neural networks on post-training quantization<\/a>, S Houache, J.-F. Aujol, Y. Traonmilin, To appear in Transactions of machine learning research, 2026.<\/p>\n

Max-sparsity atomic autoencoders with application to inverse problems<\/a>, A. Joundi, A. Newson, Y. Traonmilin,\u00a0 SSVM 2025. (EFFIREG)<\/p>\n

Parameter-free structure-texture image decomposition by unrolling,<\/a> L. Girometti, J.-F. Aujol, A. Guennec, Y. Traonmilin, accepted to SSVM 2025.<\/p>\n

Joint structure-texture low dimensional modeling for image decomposition with a plug and play framework<\/a>, A. Guennec, J.- F. Aujol, Y.\u00a0 Traonmilin,\u00a0 SIAM journal on imaging sciences, 2025. (EFFIREG)<\/p>\n<\/div>\n

Sketched over-parametrized projected gradient descent for sparse spike estimation,<\/a> P.-J. B\u00e9nard , Y.\u00a0 Traonmilin, J.- F. Aujol, Signal Processing Letters, 2024. (EFFIREG)<\/p>\n

Projected Block Coordinate Descent for sparse spike estimation<\/a>. P.-J. B\u00e9nard , Y.\u00a0 Traonmilin, J.- F Aujol, EUSIPCO 2024. (EFFIREG)<\/p>\n<\/div>\n<\/div>\n

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

A theory of optimal convex regularization for low-dimensional recovery<\/a>, Y. Traonmilin, R. Gribonval and S. Vaiter, Information and Inference, 2024.\u00a0 (EFFIREG)<\/p>\n

Estimation of off-the-grid sparse spikes with over-parametrized projected gradient descent: theory and application<\/a>. P.-J. B\u00e9nard, 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\u00a0 (EFFIREG)<\/p>\n

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

On strong basins of attractions for non-convex sparse spike estimation: upper and lower bounds<\/a>, Y. Traonmilin, J.F. Aujol, A. Leclaire and P.J. B\u00e9nard.\u00a0 JMIV, 2023. The final publication is available at https:\/\/rdcu.be\/dnjmu<\/a> . (EFFIREG).<\/p>\n

\n

Disentangled latent representations of images with atomic autoencoders,<\/a> A. Newson and Y. Traonmilin<\/strong>, SampTA 2023. (EFFIREG)<\/p>\n<\/div>\n

Compressive learning of deep regularization for denoising<\/a>, H. Shi, Y. Traonmilin, J.-F. Aujol, SSVM 2023. (EFFIREG)<\/p>\n

Piecewise linear prediction model for action tracking in sports<\/a>, A. Baldanza, J.F. Aujol, Y. Traonmilin<\/strong> and F. Alary, EUSIPCO, 2022.<\/p>\n

Fast off-the-grid sparse recovery with over-parametrized projected gradient descent<\/a>, P.J. B\u00e9nard, Y. Traonmilin<\/strong> and J.F. Aujol, EUSIPCO 2022. (EFFIREG)<\/p>\n

Compressive learning for patch-based image denoising<\/a>, H. Shi, Y. Traonmilin<\/strong> and J-F. Aujol, SIAM Journal on Imaging Sciences, 2022. (EFFIREG)<\/p>\n

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

Sur la performance des m\u00e9thodes convexes et non-convexes de reconstruction de mod\u00e8les de faible dimension en science des donn\u00e9es<\/a>, Y. Traonmilin<\/strong>, Habilitation \u00e0 diriger des recherches, 2021.<\/p>\n

D\u00e9coupage automatique de vid\u00e9os de sport amateur par d\u00e9tection de personnes et analyse de contenu colorim\u00e9trique<\/a>, A. Baldanza, J.-F. Aujol, Y. Traonmilin<\/strong> and F. Alary, ORASIS 2021.<\/p>\n

Sketched learning for image denoising<\/a>, H. Shi, Y. Traonmilin<\/strong> and J-F. Aujol, Scale Space and Variational Methods in Computer Vision, 2021. (EFFIREG)<\/p>\n

Statistical Learning Guarantees for Compressive Clustering and Compressive Mixture Modeling.<\/a> R. Gribonval, G. Blanchard, N. Keriven \u00a0and Y. Traonmilin<\/strong>, To appear in Mathematical Statistics and Learning,\u00a0 <\/strong>2021.<\/p>\n

Compressive Statistical Learning with Random Feature Moments.<\/a>\u00a0R. Gribonval, G. Blanchard, N. Keriven \u00a0and Y. Traonmilin, <\/strong>To appear in Mathematical Statistics and Learning,\u00a0<\/strong>2021.<\/p>\n

Projected gradient descent for non-convex sparse spike estimation,<\/a> IEEE Signal Processing Letters,\u00a0 Y. Traonmilin<\/strong>, J.-F. Aujol and Arthur Leclaire, 2020.<\/p>\n

\u00ab\u00a0The basins of attraction of the global minimizers of the non-convex sparse spikes estimation problem\u00a0\u00bb<\/a>, Y. Traonmilin<\/strong> and J.-F. Aujol, Inverse Problems, 2019.*<\/p>\n

Is the 1-norm the best convex sparse regularization?<\/a>, Y.\u00a0 Traonmilin, S. Vaiter and R. Gribonval, iTWIST’18, <\/i>2018.<\/p>\n

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

Stable recovery of low-dimensional cones in Hilbert spaces: One RIP to rule them all<\/a>. Applied and Computational Harmonic Analysis,\u00a0Y. Traonmilin<\/strong> and R. Gribonval, 2018.*<\/p>\n

Compressed sensing in Hilbert spaces<\/a>. \u00a0Y. Traonmilin<\/strong>, G. Puy, R. Gribonval and M. E. Davies, Compressed Sensing and Its Applications, (Book chapter), 2017.<\/p>\n

Compressive K-means<\/a>. N. Keriven, N. Tremblay, Y. Traonmilin<\/strong> and R. Gribonval, ICASSP, 2017.<\/p>\n

Phase Unmixing : Multichannel Source Separation with Magnitude Constraints<\/a>. A. Deleforge and Y. Traonmilin,\u00a0<\/strong>ICASSP, 2017.<\/p>\n

A framework for low-complexity signal recovery and its application to structured sparsity.<\/a>\u00a0Y. Traonmilin<\/strong> and R. Gribonval, 2016 IEEE Information Theory Workshop (ITW), Cambridge, pp. 156-160, \u00a0\u00a02016.<\/p>\n

Robust Multi-image Processing With Optimal Sparse Regularization. <\/a>Y. Traonmilin<\/strong>, 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<\/a>.<\/p>\n

Relations entre le mod\u00e8le d\u2019image et le nombre de mesures pour une super-r\u00e9solution fid\u00e8le<\/a>, Y. Traonmilin<\/strong>, PhD THesis, 2014<\/p>\n

Simultaneous High Dynamic Range and Super-Resolution Imaging Without Regularization<\/a>.
Y. Traonmilin<\/strong> and C. Aguerrebere, SIIMS, 2013.<\/p>\n

Quantification de la robustesse de la super-r\u00e9solution par minimisation L1<\/a>
Y. Traonmilin<\/strong>, S. Ladjal, and A. Almansa,
23\u00e8me Colloque Gretsi (Gretsi 2013), Brest : France (2013).<\/p>\n

Outlier removal power of the L1-Norm Super-Resolution<\/a>.
Y. Traonmilin<\/strong>, Sa\u00efd Ladjal, and Andr\u00e9s Almansa.
Scale Space and Variational Methods in Computer Vision, volume 7893 of Lecture Notes in Computer Science.<\/p>\n

On the amount of regularization for super-resolution reconstruction<\/a>.
Y. Traonmilin<\/strong>, Sa\u00efd Ladjal, and Andr\u00e9s Almansa, Technical report, 2012.<\/p>\n

On the amount of regularization for Super-Resolution interpolation<\/a>.
Y. Traonmilin<\/strong>, Sa\u00efd Ladjal, and Andr\u00e9s Almansa.
In 20th European Signal Processing Conference 2012 (EUSIPCO 2012), Bucharest, Romania, August 2012.<\/p>\n

Previous work (Geophysical signal processing, main author)
<\/strong><\/p>\n

Statics-preserving projection filtering.
Y. Traonmilin<\/strong> and N. Gulunay. Geophysical Prospecting, 2012.<\/p>\n

Statics preserving projection filtering.
Y. Traonmilin<\/strong> and N. Gulunay. SEG Technical Program Expanded Abstracts, 30(1):3638\u20133642, 2011.<\/p>\n

Multi-dip estimation in n dimensions.
Y. Traonmilin<\/strong>, G. Lambar\u00e9<\/span><\/span>, P. Herrmann<\/span><\/span>, N. Deladerriere<\/span><\/span> and K. Garceran<\/span>.<\/span> 71st EAGE Conference & Exhibition, 2009.<\/p>\n

Structurally consistent f-x filtering.
Y. Traonmilin<\/strong> and P. Herrmann. SEG Technical Program Expanded Abstracts, 27(1):2642\u20132646, 2008.<\/p>\n\n\n

*For : The basins of attraction of the global minimizers of the non-convex sparse spikes estimation problem<\/a> <\/p>\n\n\n\n

In equation (32), on the right side you should read ||x||^2 instead of ||Ax||^2.<\/p>\n\n\n\n

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<\/a>,)<\/p>\n\n\n\n

<\/p>\n\n\n\n

*For : Stable recovery of low-dimensional cones in Hilbert spaces: One RIP to rule them all<\/a>.<\/p>\n\n\n\n

In Fact 2.1. You should read A\u2282S(1) instead of A\u2282B(1)<\/p>\n\n\n\n

<\/p>\n\n\n\n

<\/p>\n","protected":false},"excerpt":{"rendered":"

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: Towards optimal algorithms for the recovery of low-dimensional models with linear rates , Y. Traonmilin , J.-F. Aujol, A. Guennec, 2025. (EFFIREG) Stochastic Orthogonal Regularization […]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-10","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/index.php?rest_route=\/wp\/v2\/pages\/10","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=10"}],"version-history":[{"count":20,"href":"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/index.php?rest_route=\/wp\/v2\/pages\/10\/revisions"}],"predecessor-version":[{"id":640,"href":"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/index.php?rest_route=\/wp\/v2\/pages\/10\/revisions\/640"}],"wp:attachment":[{"href":"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=10"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}