Samuel Vaiter

Publications de Samuel Vaiter
71
Documents

Publications

Publications

Deposit thumbnail

Bilevel gradient methods and the Morse parametric qualification condition

Jérôme Bolte , Quoc-Tung Le , Edouard Pauwels , Samuel Vaiter

Mathematics of Operations Research, In press, 31 p

Article dans une revue hal-04942322v3
Deposit thumbnail

Geometric and computational hardness of bilevel programming

Jérôme Bolte , Quoc-Tung Le , Edouard Pauwels , Samuel Vaiter

Mathematical Programming, Series A, In press, 32 p

Article dans une revue hal-04649435v2
Deposit thumbnail

Risk Estimate under a Time-Varying Autoregressive Model for Data-Driven Reproduction Number Estimation

Barbara Pascal , Samuel Vaiter

Signal Processing, 2025, pp.110246

Article dans une revue hal-04705913v3
Deposit thumbnail

A theory of optimal convex regularization for low-dimensional recovery

Yann Traonmilin , Rémi Gribonval , Samuel Vaiter

Information and Inference, 2024, 13 (2)

Article dans une revue hal-03467123v3
Deposit thumbnail

Gradient scarcity with Bilevel Optimization for Graph Learning

Hashem Ghanem , Samuel Vaiter , Nicolas Keriven

Transactions on Machine Learning Research Journal, 2024

Article dans une revue hal-04041721v1

Local linear convergence of proximal coordinate descent algorithm

Quentin Klopfenstein , Quentin Bertrand , Alexandre Gramfort , Joseph Salmon , S. Vaiter

Optimization Letters, 2024, 18, pp.135-154. ⟨10.1007/s11590-023-01976-z⟩

Article dans une revue hal-04308828v1
Deposit thumbnail

Convergence of Message Passing Graph Neural Networks with Generic Aggregation On Large Random Graphs

Matthieu Cordonnier , Nicolas Keriven , Nicolas Tremblay , Samuel Vaiter

Journal of Machine Learning Research, 2024, 25

Article dans une revue hal-04059402v3
Deposit thumbnail

The derivatives of Sinkhorn-Knopp converge

Edouard Pauwels , Samuel Vaiter

SIAM Journal on Optimization, 2023, 33 (3), ⟨10.48550/arXiv.2207.12717⟩

Article dans une revue hal-03736905v3
Deposit thumbnail

Supervised learning of analysis-sparsity priors with automatic differentiation

Hashem Ghanem , Joseph Salmon , Nicolas Keriven , Samuel Vaiter

IEEE Signal Processing Letters, 2023, 30, pp.339-343. ⟨10.1109/LSP.2023.3244511⟩

Article dans une revue hal-03518852v1
Deposit thumbnail

The Geometry of Sparse Analysis Regularization

Xavier Dupuis , Samuel Vaiter

SIAM Journal on Optimization, 2023, 33 (2), pp.842-867. ⟨10.1137/19M1271877⟩

Article dans une revue hal-02169356v2

Sparse and Smooth: improved guarantees for Spectral Clustering in the Dynamic Stochastic Block Model

Nicolas Keriven , Samuel Vaiter

Electronic Journal of Statistics , 2022, 16 (1), pp.1330-1366. ⟨10.1214/22-ejs1986⟩

Article dans une revue hal-02484970v1
Deposit thumbnail

Implicit differentiation for fast hyperparameter selection in non-smooth convex learning

Quentin Bertrand , Quentin Klopfenstein , Mathurin Massias , Mathieu Blondel , Samuel Vaiter et al.

Journal of Machine Learning Research, 2022, 23 (1), pp.6680 - 6722

Article dans une revue hal-03228663v2

Linear support vector regression with linear constraints

Quentin Klopfenstein , Samuel Vaiter

Machine Learning, 2021, 110 (7), pp.1939-1974. ⟨10.1007/s10994-021-06018-2⟩

Article dans une revue hal-03303248v1
Deposit thumbnail

Automated data-driven selection of the hyperparameters for Total-Variation based texture segmentation

Barbara Pascal , Samuel Vaiter , Nelly Pustelnik , Patrice Abry

Journal of Mathematical Imaging and Vision, 2021, 63, pp.923-952. ⟨10.1007/s10851-021-01035-1⟩

Article dans une revue hal-03044181v1
Deposit thumbnail

Block based refitting in $\ell_{12}$ sparse regularisation

Charles-Alban Deledalle , Nicolas Papadakis , Joseph Salmon , Samuel Vaiter

Journal of Mathematical Imaging and Vision, 2021, 63, pp.216-236. ⟨10.1007/s10851-020-00993-2⟩

Article dans une revue hal-02330441v1
Deposit thumbnail

Dual Extrapolation for Sparse Generalized Linear Models

Mathurin Massias , Samuel Vaiter , Alexandre Gramfort , Joseph Salmon

Journal of Machine Learning Research, 2020, 21 (234), pp.1-33

Article dans une revue hal-02263500v1
Deposit thumbnail

Maximal Solutions of Sparse Analysis Regularization

Abdessamad Barbara , Abderrahim Jourani , Samuel Vaiter

Journal of Optimization Theory and Applications, 2019, 180 (2), pp.374-396. ⟨10.1007/s10957-018-1385-3⟩

Article dans une revue hal-01467965v1
Deposit thumbnail

Model Consistency of Partly Smooth Regularizers

Samuel Vaiter , Gabriel Peyré , Jalal M. Fadili

IEEE Transactions on Information Theory, 2018, 64 (3), pp.1725-1737. ⟨10.1109/TIT.2017.2713822⟩

Article dans une revue hal-01658847v1
Deposit thumbnail

CLEAR: Covariant LEAst-Square Refitting with Applications to Image Restoration

Charles-Alban Deledalle , Nicolas Papadakis , Joseph Salmon , Samuel Vaiter

SIAM Journal on Imaging Sciences, 2017, 10 (1), pp.243-284. ⟨10.1137/16M1080318⟩

Article dans une revue hal-01333295v3
Deposit thumbnail

The degrees of freedom of partly smooth regularizers

Samuel Vaiter , Charles-Alban Deledalle , Jalal M. Fadili , Gabriel Peyré , Charles H Dossal

Annals of the Institute of Statistical Mathematics, 2017, 69 (4), pp.791 - 832. ⟨10.1007/s10463-016-0563-z⟩

Article dans une revue hal-00981634v4
Deposit thumbnail

Accelerated Alternating Descent Methods for Dykstra-like problems

Antonin Chambolle , Pauline Tan , Samuel Vaiter

Journal of Mathematical Imaging and Vision, 2017, 59 (3), pp.481-497. ⟨10.1007/s10851-017-0724-6⟩

Article dans une revue hal-01346532v1
Deposit thumbnail

A sharp oracle inequality for Graph-Slope

Pierre C. Bellec , Joseph Salmon , Samuel Vaiter

Electronic Journal of Statistics , 2017, 11 (2), pp.4851-4870. ⟨10.1214/17-EJS1364⟩

Article dans une revue hal-01544680v1
Deposit thumbnail

Model Selection with Low Complexity Priors

Samuel Vaiter , Mohammad Golbabaee , Jalal M. Fadili , Gabriel Peyré

Information and Inference, 2015, 52 p

Article dans une revue hal-00842603v3
Deposit thumbnail

Stein Unbiased GrAdient estimator of the Risk (SUGAR) for multiple parameter selection

Charles-Alban Deledalle , Samuel Vaiter , Jalal M. Fadili , Gabriel Peyré

SIAM Journal on Imaging Sciences, 2014, 7 (4), pp.2448-2487

Article dans une revue hal-00987295v2
Deposit thumbnail

Robust Sparse Analysis Regularization

Samuel Vaiter , Gabriel Peyré , Charles H Dossal , Jalal M. Fadili

IEEE Transactions on Information Theory, 2013, 59 (4), pp.2001-2016. ⟨10.1109/TIT.2012.2233859⟩

Article dans une revue hal-00627452v5
Deposit thumbnail

Local Behavior of Sparse Analysis Regularization: Applications to Risk Estimation

Samuel Vaiter , Charles Deledalle , Gabriel Peyré , Charles H Dossal , Jalal M. Fadili

Applied and Computational Harmonic Analysis, 2013, 35 (3), pp.433-451. ⟨10.1016/j.acha.2012.11.006⟩

Article dans une revue hal-00687751v2

Differentiable Generalized Sliced Wasserstein Plans

Laetitia Chapel , Romain Tavenard , Samuel Vaiter

NeurIPS 2025 - 39th Annual Conference on Neural Information Processing Systems, Dec 2025, San Diego, United States. pp.1-20, ⟨10.48550/arXiv.2505.22049⟩

Communication dans un congrès hal-05345011v1
Deposit thumbnail

Learning Theory for Kernel Bilevel Optimization

Fares El Khoury , Edouard Pauwels , Samuel Vaiter , Michael Arbel

NeurIPS 2025 - 39th Annual Conference on Neural Information Processing Systems, Dec 2025, San Diego, United States. pp.1-47

Communication dans un congrès hal-04950585v3
Deposit thumbnail

Provable local learning rule by expert aggregation for a Hawkes network

Sophie Jaffard , Samuel Vaiter , Alexandre Muzy , Patricia Reynaud-Bouret

AISTATS 2024 - The 27th International Conference on Artificial Intelligence and Statistics, May 2024, Valence, Spain

Communication dans un congrès hal-04065229v2
Deposit thumbnail

A lower bound and a near-optimal algorithm for bilevel empirical risk minimization

Mathieu Dagréou , Thomas Moreau , Samuel Vaiter , Pierre Ablin

International Conference on Artificial Intelligence and Statistics (AISTATS), May 2024, Valencia, Spain. ⟨10.48550/arXiv.2302.08766⟩

Communication dans un congrès hal-04302861v3
Deposit thumbnail

Seeking universal approximation for continuous limits of graph neural networks on large random graphs

Matthieu Cordonnier , Nicolas Keriven , Nicolas Tremblay , Samuel Vaiter

Asilomar 2024 - Asilomar Conference on Signals, Systems, and Computers, Oct 2024, Pacific Grove, United States. pp.1-5

Communication dans un congrès hal-04831761v1
Deposit thumbnail

Derivatives of Stochastic Gradient Descent in parametric optimization

Franck Iutzeler , Edouard Pauwels , S. Vaiter

Advances in Neural Information Processing Systems (NeurIPS), Dec 2024, Vancouver, Canada, Canada. 24 p

Communication dans un congrès hal-04582212v2
Deposit thumbnail

Seeking universal approximation for continuous counterparts of GNNs on large random graphs

Matthieu Cordonnier , Nicolas Keriven , Nicolas Tremblay , Samuel Vaiter

GSP 2024 - 7th Graph Signal Processing Workshop, Jun 2024, Delft, Netherlands

Communication dans un congrès hal-04728922v1
Deposit thumbnail

Convergence of Message Passing Graph Neural Networks with Generic Aggregation On Random Graphs

Matthieu Cordonnier , Nicolas Keriven , Nicolas Tremblay , Samuel Vaiter

GSP 2023 - 6th Graph Signal Processing workshop, Jun 2023, Oxford, United Kingdom. pp.1-3

Communication dans un congrès hal-04106511v1
Deposit thumbnail

Convergence of Graph Neural Networks with generic aggregation functions on random graphs

Matthieu Cordonnier , Nicolas Keriven , Nicolas Tremblay , Samuel Vaiter

GRETSI 2023 - XXIXème Colloque Francophone de Traitement du Signal et des Images, GRETSI - Groupe de Recherche en Traitement du Signal et des Images, Aug 2023, Grenoble, France. pp.1-4

Communication dans un congrès hal-04373554v1
Deposit thumbnail

On the Robustness of Text Vectorizers

Rémi Catellier , Samuel Vaiter , Damien Garreau

ICML 2023 - Fortieth International Conference on Machine Learning, Jul 2023, Honolulu, United States

Communication dans un congrès hal-04403681v1

One-step differentiation of iterative algorithms

Jérôme Bolte , Edouard Pauwels , Samuel Vaiter

Advances in Neural Information Processing Systems, 2023, New Orleans, United States

Communication dans un congrès hal-04104382v1
Deposit thumbnail

What functions can Graph Neural Networks compute on random graphs? The role of Positional Encoding

Nicolas Keriven , Samuel Vaiter

NeurIPS 2023 - 37th Annual Conference on Neural Information Processing Systems, Dec 2023, New-Orleans, United States. pp.1-28

Communication dans un congrès hal-04103771v1
Deposit thumbnail

Automatic differentiation of nonsmooth iterative algorithms

Jérôme Bolte , Edouard Pauwels , Samuel Vaiter

Advances in Neural Information Processing Systems, Nov 2022, New Orleans, United States. 28 p

Communication dans un congrès hal-03681143v1
Deposit thumbnail

A framework for bilevel optimization that enables stochastic and global variance reduction algorithms

Mathieu Dagréou , Pierre Ablin , Samuel Vaiter , Thomas Moreau

Advances in Neural Information Processing Systems (NeurIPS), Nov 2022, New Orleans, United States

Communication dans un congrès hal-03562151v2
Deposit thumbnail

Benchopt: Reproducible, efficient and collaborative optimization benchmarks

Thomas Moreau , Mathurin Massias , Alexandre Gramfort , Pierre Ablin , Pierre-Antoine Bannier et al.

NeurIPS 2022 - 36. Conference on Neural Information Processing Systems, Nov 2022, La Nouvelle Orléans, United States

Communication dans un congrès hal-03830604v1

On the Universality of Graph Neural Networks on Large Random Graphs

Nicolas Keriven , Alberto Bietti , Samuel Vaiter

NeurIPS 2021 - 35th Conference on Neural Information Processing Systems, Dec 2021, Virtual, Canada

Communication dans un congrès hal-03382553v1

Convergence and Stability of Graph Convolutional Networks on Large Random Graphs

Nicolas Keriven , Alberto Bietti , Samuel Vaiter

NeurIPS 2020 - 34th Conference on Neural Information Processing Systems, Dec 2020, Vancouver (virtual), Canada

Communication dans un congrès hal-02976711v1
Deposit thumbnail

Implicit differentiation of Lasso-type models for hyperparameter optimization

Quentin Bertrand , Quentin Klopfenstein , Mathieu Blondel , Samuel Vaiter , Alexandre Gramfort et al.

ICML 2020 - 37th International Conference on Machine Learning, Jul 2020, Vienna / Virtuel, Austria

Communication dans un congrès hal-02532683v2
Deposit thumbnail

Refitting solutions promoted by $\ell_{12}$ sparse analysis regularization with block penalties

Charles-Alban Deledalle , Nicolas Papadakis , Joseph Salmon , Samuel Vaiter

International Conference on Scale Space and Variational Methods in Computer Vision (SSVM'19), Jun 2019, Hofgeismar, Germany. pp.131-143, ⟨10.1007/978-3-030-22368-7_11⟩

Communication dans un congrès hal-02059006v1
Deposit thumbnail

Exploiting regularity in sparse Generalized Linear Models

Mathurin Massias , Samuel Vaiter , Alexandre Gramfort , Joseph Salmon

SPARS 2019 - Signal Processing with Adaptive Sparse Structured Representations, Jul 2019, Toulouse, France

Communication dans un congrès hal-02288859v1
Deposit thumbnail

Is the 1-norm the best convex sparse regularization?

Yann Traonmilin , Samuel Vaiter , Rémi Gribonval

iTWIST'18 - international Traveling Workshop on Interactions between low-complexity data models and Sensing Techniques, Nov 2018, Marseille, France. pp.1-11

Communication dans un congrès hal-01819219v1
Deposit thumbnail

Optimality of 1-norm regularization among weighted 1-norms for sparse recovery: a case study on how to find optimal regularizations

Yann Traonmilin , Samuel Vaiter

8th International Conference on New Computational Methods for Inverse Problems, May 2018, Paris, France. pp.conference 1, ⟨10.1088/1742-6596/1131/1/012009⟩

Communication dans un congrès hal-01720871v3
Deposit thumbnail

Characterizing the maximum parameter of the total-variation denoising through the pseudo-inverse of the divergence

Charles-Alban Deledalle , Nicolas Papadakis , Joseph Salmon , Samuel Vaiter

Signal Processing with Adaptive Sparse Structured Representations (SPARS'17), Jun 2017, Lisbon, Portugal

Communication dans un congrès hal-01412059v1
Deposit thumbnail

Stable Recovery with Analysis Decomposable Priors

Jalal M. Fadili , Gabriel Peyré , Samuel Vaiter , Charles-Alban Deledalle , Joseph Salmon

Proc. SampTA'13, Jul 2013, Bremen, Germany. pp.113-116

Communication dans un congrès hal-00926732v1
Deposit thumbnail

Robustesse au bruit des régularisations polyhédrales

Samuel Vaiter , Gabriel Peyré , Jalal M. Fadili

24th GRETSI Symposium on Signal and Image Processing, Sep 2013, Brest, France. pp.ID130

Communication dans un congrès hal-00927075v1
Deposit thumbnail

Stable Recovery with Analysis Decomposable Priors

Jalal M. Fadili , Gabriel Peyré , Samuel Vaiter , Charles-Alban Deledalle , Joseph Salmon

SPARS 2013, Jul 2013, Lausanne, Switzerland. 1 pp

Communication dans un congrès hal-00926727v1
Deposit thumbnail

The degrees of freedom of the group Lasso for a general design

Samuel Vaiter , Gabriel Peyré , Jalal M. Fadili , Charles-Alban Deledalle , Charles H Dossal

SPARS'13, Jul 2013, Lausanne, Switzerland. 1 page

Communication dans un congrès hal-00926929v1
Deposit thumbnail

Reconstruction Stable par Régularisation Décomposable Analyse

Jalal M. Fadili , Gabriel Peyré , Samuel Vaiter , Charles-Alban Deledalle , Joseph Salmon

Colloque sur le Traitement du Signal et des Images (GRETSI'13), Sep 2013, Brest, France. pp.ID208

Communication dans un congrès hal-00927561v1
Deposit thumbnail

Robust Polyhedral Regularization

Samuel Vaiter , Gabriel Peyré , Jalal M. Fadili

International Conference on Sampling Theory and Applications (SampTA), 2013, Bremen, Germany

Communication dans un congrès hal-00816377v1
Deposit thumbnail

Unbiased Risk Estimation for Sparse Analysis Regularization

Charles Deledalle , Samuel Vaiter , Gabriel Peyré , Jalal M. Fadili , Charles H Dossal

Proc. ICIP'12, Sep 2012, Orlando, United States. pp.3053-3056

Communication dans un congrès hal-00662718v1
Deposit thumbnail

Proximal Splitting Derivatives for Risk Estimation

Charles Deledalle , Samuel Vaiter , Gabriel Peyré , Jalal M. Fadili , Charles H Dossal

NCMIP'12, Apr 2012, France. pp.012003, ⟨10.1088/1742-6596/386/1/012003⟩

Communication dans un congrès hal-00670213v1
Deposit thumbnail

The Degrees of Freedom of the Group Lasso

Samuel Vaiter , Charles Deledalle , Gabriel Peyré , Jalal M. Fadili , Charles H Dossal

International Conference on Machine Learning Workshop (ICML), 2012, Edinburgh, United Kingdom

Communication dans un congrès hal-00695292v1
Deposit thumbnail

Risk estimation for matrix recovery with spectral regularization

Charles-Alban Deledalle , Samuel Vaiter , Gabriel Peyré , Jalal M. Fadili , Charles H Dossal

ICML'2012 workshop on Sparsity, Dictionaries and Projections in Machine Learning and Signal Processing, Jun 2012, Edinburgh, United Kingdom

Communication dans un congrès hal-00695326v3
Deposit thumbnail

Low Complexity Regularization of Inverse Problems

Samuel Vaiter

General Mathematics [math.GM]. Université Paris Dauphine - Paris IX, 2014. English. ⟨NNT : 2014PA090055⟩

Thèse tel-01130672v1
Deposit thumbnail

Low Complexity Regularizations of Inverse Problems

Samuel Vaiter

Information Theory [math.IT]. Université Paris Dauphine - Paris IX, 2014. English. ⟨NNT : ⟩

Thèse tel-01026398v1
Deposit thumbnail

From optimization to algorithmic differentiation: a graph detour

Samuel Vaiter

Optimization and Control [math.OC]. Université de Bourgogne, 2021

HDR tel-03159975v1