Gabriel Peyré
Publications
Publications
|
|
Model Consistency of Partly Smooth Regularizers[Research Report] CNRS. 2014 |
|
|
Transformative or Conservative? Conservation laws for ResNets and Transformers42nd International Conference on Machine Learning (ICML 2025), Jul 2025, Vancouver (Canada), Canada |
|
|
Towards Understanding the Universality of Transformers for Next-Token PredictionICLR 2025, Apr 2025, Singapore, Singapore |
|
|
Transformers are Universal In-context LearnersICLR 2025, Apr 2025, Singapour, Singapore |
|
|
Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective40th International Conference on Machine Learning, Jun 2023, Honolulu, Hawaï, United States. pp.29919-29936 |
|
|
Abide by the Law and Follow the Flow: Conservation Laws for Gradient FlowsThirty-seventh Conference on Neural Information Processing Systems, Dec 2023, New Orleans (Louisiane), United States |
|
|
On global convergence of ResNets: From finite to infinite width using linear parameterizationNeurIPS 2022, Nov 2022, New Orleans (online), United States. pp.16385-16397 |
|
|
Sinkformers: Transformers with Doubly Stochastic AttentionInternational Conference on Artificial Intelligence and Statistics, Mar 2022, Virtuel, France. pp.3515-3530 |
|
|
Randomized Stochastic Gradient Descent Ascent25th International Conference on Artificial Intelligence and Statistics, Mar 2022, Online, France |
|
|
Do Residual Neural Networks discretize Neural Ordinary Differential Equations?NeurIPS'22, Dec 2022, New Orleans (Louisiana), United States |
|
|
Unsupervised Ground Metric Learning Using Wasserstein Singular VectorsProceedings of the 39th International Conference on Machine Learning,, Jul 2022, Baltimore, United States |
|
|
Faster Unbalanced Optimal Transport: Translation invariant Sinkhorn and 1-D Frank-WolfeProceedings of The 25th International Conference on Artificial Intelligence and Statistics, Mar 2022, 2022-03-28, France. pp.4995-5021 |
|
|
Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and CostsICML'22, Jul 2022, Baltimore, United States |
|
|
Fast and accurate optimization on the orthogonal manifold without retraction25th International Conference on Artificial Intelligence and Statistics, Mar 2022, Virtual, France. pp.5636-5657 |
|
|
Momentum Residual Neural Networks38th International Conference on Machine Learning, Aug 2021, Online, United States. pp.9276-9287, ⟨10.48550/arXiv.2102.07870⟩ |
|
|
Super-efficiency of automatic differentiation for functions defined as a minimumInternational Conference on Machine Learning, Aug 2020, Vienna, Austria |
|
|
Faster Wasserstein Distance Estimation with the Sinkhorn DivergenceNeurIPS 2020, Dec 2020, Vancouver, Canada. pp.2257-2269 |
|
|
Wasserstein Control of Mirror Langevin Monte CarloProceedings of Machine Learning Research, Conference on Learning Theory (COLT), Jul 2020, Graz, Austria. pp.1-28, ⟨10.48550/arXiv.2002.04363⟩ |
|
|
Entropic Optimal Transport between Unbalanced Gaussian Measures has a Closed FormNeurIPS 2020 - 34th Conference on Neural Information Processing Systems, Dec 2020, Vancouver / Virtuel, Canada |
|
|
Geometric Losses for Distributional LearningProceedings of the International Conference on Machine Learning, 2019, Long Beach, United States |
|
|
Universal Invariant and Equivariant Graph Neural NetworksAdvances in Neural Information Processing Systems (NeurIPS), 2019, Vancouver, Canada |
|
|
Support Localization and the Fisher Metric for off-the-grid Sparse RegularizationInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2019, Naha, Japan |
|
|
The Sliding Frank-Wolfe Algorithm for the BLASSOWorkshop on Signal Processing with Adaptative Sparse Structured Representations - SPARS 2019, Sep 2019, Toulouse, France |
|
|
Sample Complexity of Sinkhorn divergencesAISTATS'19 - 22nd International Conference on Artificial Intelligence and Statistics, Apr 2019, Okinawa, Japan |
|
|
Learning Generative Models with Sinkhorn DivergencesAISTATS, Apr 2018, Lanzarote, Spain |
|
|
Optimal Transport for Diffeomorphic RegistrationMICCAI 2017, Sep 2017, Quebec, Canada |
|
|
A Multi-step Inertial Forward–Backward Splitting Method for Non-convex OptimizationAdvances in Neural Information Processing Systems (NIPS), Dec 2017, Barcelona, Spain |
|
|
Optimal transport-based dictionary learning and its application to Euclid-like Point Spread Function representationWavelets and Sparsity XVII, Aug 2017, San Diego, United States. pp.103940H, ⟨10.1117/12.2270641⟩ |
|
|
Déconvolution parcimonieuse sans grille: une méthode de faible rangORASIS 2017 - Journées francophones des jeunes chercheurs en vision par ordinateur, GREYC, Jun 2017, Colleville-sur-Mer, France |
|
|
Gromov-Wasserstein Averaging of Kernel and Distance MatricesICML 2016, Jun 2016, New-York, United States |
|
|
Stochastic Optimization for Large-scale Optimal TransportNIPS 2016 - Thirtieth Annual Conference on Neural Information Processing System, Dec 2016, Barcelona, Spain |
|
|
Sparse Support Recovery with Non-smooth Loss FunctionsAdvances in Neural Information Processing Systems (NIPS), Nov 2015, Barcelone, Spain |
|
|
Fast Optimal Transport Averaging of Neuroimaging DataInformation Processing in Medical Imaging (IPMI), Jun 2015, Isle of Skye, United Kingdom |
|
|
Asymptotic of Sparse Support Recovery for Positive Measures5th International Workshop on New Computational Methods for Inverse Problems (NCMIP2015), 2015, Cachan, France. ⟨10.1088/1742-6596/657/1/012013⟩ |
|
|
Local Linear Convergence of Forward--Backward under Partial SmoothnessAdvances in Neural Information Processing Systems (NIPS), Dec 2014, Montréal, Canada |
|
|
Iteration-Complexity of a Generalized Forward Backward Splitting AlgorithmICASSP'14, May 2014, Florence, Italy. 5 pp |
|
|
On the Convergence Rates of Proximal Splitting AlgorithmsIEEE International Conference on Image Processing (ICIP 2014), Oct 2014, Paris, France |
|
|
Robust Polyhedral RegularizationInternational Conference on Sampling Theory and Applications (SampTA), 2013, Bremen, Germany |
|
|
Reconstruction Stable par Régularisation Décomposable AnalyseColloque sur le Traitement du Signal et des Images (GRETSI'13), Sep 2013, Brest, France. pp.ID208 |
|
|
Stein COnsistent Risk Estimator (SCORE) for hard thresholdingSignal Processing with Adaptive Sparse Structured Representations., Jul 2013, Lausanne, Switzerland |
|
|
Constrained Sparse Texture SynthesisProceedings of SSVM'13, Jun 2013, Seggauberg, Austria |
|
|
Synthèse de texture par décomposition parcimonieuse contrainteGretsi 2013, Sep 2013, Brest, France |
|
|
Stable Recovery with Analysis Decomposable PriorsProc. SampTA'13, Jul 2013, Bremen, Germany. pp.113-116 |
|
|
Regularized Discrete Optimal TransportInternational Conference on Scale Space and Variational Methods in Computer Vision (SSVM'13), Jun 2013, Schloss Seggau, Leibnitz, Austria. pp.428-439, ⟨10.1007/978-3-642-38267-3_36⟩ |
|
|
Robustesse au bruit des régularisations polyhédrales24th GRETSI Symposium on Signal and Image Processing, Sep 2013, Brest, France. pp.ID130 |
|
|
Stable Recovery with Analysis Decomposable PriorsSPARS 2013, Jul 2013, Lausanne, Switzerland. 1 pp |
|
|
The degrees of freedom of the group Lasso for a general designSPARS'13, Jul 2013, Lausanne, Switzerland. 1 page |
|
|
Compact Representations of Stationary Dynamic TexturesICIP'12, Sep 2012, United States |
|
|
Proximal Splitting Derivatives for Risk EstimationNCMIP'12, Apr 2012, France. pp.012003, ⟨10.1088/1742-6596/386/1/012003⟩ |
|
|
Unbiased Risk Estimation for Sparse Analysis RegularizationProc. ICIP'12, Sep 2012, Orlando, United States. pp.3053-3056 |
|
|
Sparse reconstruction from a limited projection number of the coronary artery tree in X-ray rotational imagingIEEE International Symposium on Biomedical Imaging (ISBI'12), May 2012, Barcelone, Spain. pp.804-807 |
|
|
Wasserstein Active ContoursICIP'12, Sep 2012, Orlando, United States. pp.2541 - 2544, ⟨10.1109/ICIP.2012.6467416⟩ |
|
|
The Degrees of Freedom of the Group LassoInternational Conference on Machine Learning Workshop (ICML), 2012, Edinburgh, United Kingdom |
|
|
Risk estimation for matrix recovery with spectral regularizationICML'2012 workshop on Sparsity, Dictionaries and Projections in Machine Learning and Signal Processing, Jun 2012, Edinburgh, United Kingdom |
|
|
The degrees of freedom of the Lasso in underdetermined linear regression modelsSPARS 2011, Jul 2011, Edinburgh, United Kingdom. pp.56 |
|
|
Synthèse de textures par transport optimalGRETSI'11, 2011, France |
|
|
Non-local Active ContoursSSVM'11: 3rd International Conference on Scale Space and Variational Methods in Computer Vision, May 2011, Ein-Gedi, Israel |
|
|
Wasserstein Regularization of Imaging ProblemsICIP 2011 : 2011 IEEE International Conference on Image Processing, Sep 2011, Bruxelles, Belgium |
|
|
Wasserstein Barycenter and its Application to Texture MixingSSVM'11, 2011, Israel. pp.435-446 |
|
|
Texture Segmentation via Non-local Non-parametric Active ContoursEMMCVPR, Jul 2011, Saint Petersburg, Russia. pp.74-88 |
|
|
Learning Analysis Sparsity PriorsSampta'11, 2011, Singapour, Singapore. 4 pp |
|
|
Adaptive Structured Block Sparsity Via Dyadic PartitioningEUSIPCO 2011, Aug 2011, Barcolona, Spain. pp.1455-1459 |
|
|
Apprentissage d'a priori analyseGRETSI'11, 2011, Bordeaux, France. 4 pp |
|
|
Régularisation de Wasserstein. Application au Transfert de CouleurGRETSI'11, 2011, France |
|
|
Non-local Segmentation and InpaitingICIP'11: IEEE International Conference on Image Processing, Sep 2011, Brussels, Belgium |
|
|
Group Sparsity with Overlapping Partition FunctionsEUSIPCO 2011, Aug 2011, Barcelona, Spain. pp.303-307 |
|
|
Parcimonie Adaptative Structurée par Blocs DyadiquesGRETSI'11, 2011, Bordeaux, France. 4 pp |
|
|
On Growth and Formlets: Sparse Multi-Scale Coding of Planar ShapeCVPR'10, Jun 2010, San-Francisco, United States. pp.459-466 |
|
|
Geodesic Shape Retrieval via Optimal Mass Transport11th European Conference on Computer Vision, Sep 2010, Heraklion, Crete, Greece. pp.771-784, ⟨10.1007/978-3-642-15555-0_56⟩ |
|
|
Separation of Traveling Waves in Cortical Networks Using Optical ImagingIEEE International Symposium on Biomedical Imaging (ISBI) 2010, Apr 2010, Rotterdam, Netherlands. pp.868-871, ⟨10.1109/ISBI.2010.5490124⟩ |
Image Compression with Anisotropic Geodesic Triangulation2010 SIAM Conference on Imaging Science. Minisymposium on Anisotropic Fast Marching and Applications, Apr 2010, Chicago, USA, United States |
|
|
|
A Numerical Exploration of Compressed Sampling RecoverySPARS'09, Signal Processing with Adaptive Sparse Structured Representations, Apr 2009, Saint-Malo, France. 5p |
|
|
Best Basis Denoising with Non-stationary Wavelet PacketsICIP'09, Nov 2009, Cairo, Egypt. pp.3825-3828, ⟨10.1109/ICIP.2009.5414264⟩ |
|
|
Total Variation Projection with First Order SchemesICIP'09, Nov 2009, Cairo, Egypt. pp.1325-1328 |
|
|
Extraction of Tubular Structures over an Orientation DomainIEEE Conference on Computer Vision and Pattern Recognition (CVPR'09), Jun 2009, Florida, United States |
|
|
Challenging Restricted Isometry Constants with Greedy PursuitITW'09, Oct 2009, Taormina, Italy. pp.475-479 |
|
|
Image Compression with Anisotropic Geodesic TriangulationsIEEE 12th International Conference o Computer Vision, Sep 2009, Kyoto, Japan. pp.2343-2348, ⟨10.1109/ICCV.2009.5459425⟩ |
|
|
Extraction de textures localement parallèles par un espace de Hilbert adaptéGretsi'09, Sep 2009, Dijon, France |
|
|
Locally Parallel Textures Modeling with Adapted Hilbert SpacesEnergy Minimization Methods in Computer Vision and Pattern Recognition 2009, Aug 2009, Bonn, Germany. pp.429-442, ⟨10.1007/978-3-642-03641-5⟩ |
|
|
Algorithmes de premier ordre pour la projection sur une contrainte de variation totaleGretsi'09, Sep 2009, Dijon, France |
|
|
Une exploration numérique des performances de l'échantillonage compresséGretsi'09, Sep 2009, Dijon, France |
|
|
Compression d'images par triangulation géodésique anisotropeGretsi'09, Sep 2009, Dijon, France |
|
|
Anisotropic geodesics for perceptual grouping and domain meshing10th European Conference on Computer Vision, Oct 2008, Marseille, France. pp.129-142, ⟨10.1007/978-3-540-88688-4_10⟩ |
|
|
Non-local Regularization of Inverse ProblemsEuropean Conference on Computer Vision (ECCV'08), Oct 2008, Marseilles, France. pp.57-68 |
|
|
3D Shape Matching by Geodesic EccentricitySearch in 3D 2008, Jun 2008, Anchorage, Alaska, United States. pp.1-8, ⟨10.1109/CVPRW.2008.4563032⟩ |
|
|
Anisotropic Geodesics for Perceptual Grouping and Domain MeshingECCV 2008, Oct 2009, Marseille, France. pp.129-142 |
|
|
Non-local Regularization of Inverse Problems10th European Conference on Computer Vision, Oct 2008, Marseille, France. pp.57-68, ⟨10.1007/978-3-540-88690-7_5⟩ |
|
|
Dynamic Texture Synthesis with GroupletsMAPMO workshop on image processing, Apr 2008, Orléans, France |
|
|
Non-negative Sparse Modeling of TexturesSSVM'07, Jun 2007, Ischia, Italy. pp.628-639 |
|
|
Geometric Estimation with Orthogonal Bandlet BasesSPIE Wavelets XII, Aug 2007, San Diego, CA, United States. pp.67010M.1-67010M.10 |
|
|
Apprentissage de dictionnaires parcimonieux adaptés pour la séparation d'imagesGretsi'07, Sep 2007, Troyes, France. pp.9-12 |
|
|
Débruitage géométrique d'images dans des bases orthonormées de bandelettesGRETSI'07, Sep 2007, Troyes, France. pp.969-972 |
|
|
Critère d'identifiabilité pour la minimisation L1GRETSI'07, Sep 2007, Troye, France. pp.993-996 |
|
|
Texture Synthesis and Modification with a Patch-Valued Wavelet TransformScale Space and Variational Methods in Computer Vision (SSVM'07), Jun 2007, Ischia, Italy. pp.640-651, ⟨10.1007/978-3-540-72823-8⟩ |
|
|
Shape Matching Using the Geodesic Eccentricity Transform - A Study31st annual workshop of the Austrian Association for Pattern (OAGM/AAPR), Aug 2007, Krumbach, Austria. pp.97--104 |
|
|
Learning Adapted Dictionaries for Geometry and Texture SeparationSPIE Wavelets XII, Aug 2007, San Diego, CA, United States. pp.67011T |
|
|
Best Basis Compressed SensingScale Space and Variational Methods in Computer Vision (SSVM'07), Jun 2007, Ischia, Italy. pp.80-91, ⟨10.1007/978-3-540-72823-8_8⟩ |
|
|
Landmark-based Geodesic Computation for Heuristically Driven Path Planning2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06), Jun 2006, New York, NY, United States. pp.2229-2236, ⟨10.1109/CVPR.2006.163⟩ |
|
|
Random Sensing of Geometric ImagesNeuroComp'06, Oct 2006, Pont-à-Mousson, France. pp.91-94 |
|
|
Discrete bandelets with geometric orthogonal filtersIEEE International Conference on Image Processing, 2005. (ICIP 2005), Sep 2005, Genova, Italy. pp.65-68, ⟨10.1109/ICIP.2005.1529688⟩ |
|
|
Heuristically Driven Front Propagation for Geodesic Paths ExtractionVariational, Geometric, and Level Set Methods in Computer Vision (VLSM'05), Oct 2005, Beijing, China. pp.173-185, ⟨10.1007/11567646⟩ |
|
|
Remaillage géodésique par propagation de frontsRFIA'04, Jan 2004, Toulouse, France |
|
|
Surface Segmentation Using Geodesic Centroidal Tesselation3DPVT'04, Sep 2004, Tessaloniki, Greece. pp.995-1002 |
|
|
Geodesic Remeshing Using Front PropagationVLSM'03, Sep 2003, Nice, France. pp.33-40 |
Variational methods in imaging and geometric controlde Gruyter, 18, 2017, Radon Series on Comput. and Applied Math |
|
Special issue on Mathematics and Image Analysis in Journal of Mathematical Imaging and Vision48 (2), pp.203-382, 2014 |
|
|
Low Complexity Regularization of Linear Inverse ProblemsSampling Theory, a Renaissance, Pfander, Götz E. (Ed.), 50 p., 2015, 978-3-319-19748-7. ⟨10.1007/978-3-319-19749-4⟩ |
|
|
Geodesic Methods for Shape and Surface ProcessingTavares, João Manuel R.S.; Jorge, R.M. Natal. Advances in Computational Vision and Medical Image Processing: Methods and Applications, Springer Verlag, pp.29-56, 2009, Computational Methods in Applied Sciences, Vol. 13, ⟨10.1007/978-1-4020-9086-8⟩ |
|
|
Traitement géométrique des images par bandelettesSMF. Journée annuelle de la SMF, SMF, pp.36-69, 2006, Journée annuelle de la SMF, "Mathématiques et vision" |
|
|
Geodesic Computations for Fast and Accurate Surface Remeshing and ParameterizationProgress in Nonlinear Differential Equations and Their Applications, Birkhäuser Basel, pp.157-171, 2005, Progress in Nonlinear Differential Equations and Their Applications, Vol. 63, ⟨10.1007/3-7643-7384-9⟩ |
|
|
Le traitement numérique des images2011 |
|
|
Géométrie multi-échelles pour les images et les texturesMathématiques [math]. Ecole Polytechnique X, 2005. Français. ⟨NNT : ⟩ |