#+title: Publications

* 2026

- S. Jaffard, S. Vaiter, and P. Reynaud-Bouret. *CHANI: Correlation-based Hawkes Aggregation of Neurons with bio-Inspiration.* /Journal of Machine Learning Research./ [[https://arxiv.org/abs/2405.18828][arXiv]]
- C. Daniele, S. Villa, S. Vaiter, and L. Calatroni. *Deep Equilibrium models for Poisson Imaging Inverse problems via Mirror Descent.* /SIAM Journal on Imaging Sciences./ [[https://doi.org/10.1137/25M1779048][DOI]] [[https://arxiv.org/abs/2507.11461][arXiv]]
- J. Bolte, T. Lê, E. Pauwels, and S. Vaiter. *Bilevel gradient methods and Morse parametric qualification.* /Mathematics of Operations Research./ [[https://doi.org/10.1287/moor.2025.0914][DOI]] [[https://arxiv.org/abs/2502.09074][arXiv]]
- M. Taimeskhanov, S. Vaiter, and D. Garreau. *Towards Understanding Steering Strength.* /International Conference on Machine Learning (ICML)./ [[https://arxiv.org/abs/2602.02712][arXiv]]
- S. Tanji, S. Vaiter, and Y. Laguel. *Fairness-informed Pareto Optimization: An Efficient Bilevel Framework.* /Preprint./ [[https://arxiv.org/abs/2601.13448][arXiv]]
- M. Rando, and S. Vaiter. *ZOBA: An Efficient Single-loop Zeroth-order Bilevel Optimization Algorithm.* /Preprint./ [[https://arxiv.org/abs/2601.21836][arXiv]]
- M. Rando, and S. Vaiter. *On the Hardness of Junking LLMs.* /Preprint./ [[https://arxiv.org/abs/2605.05116][arXiv]]
- G. Lauga, C. Molinari, and S. Vaiter. *Proximal basin hopping: global optimization with guarantees.* /Preprint./ [[https://arxiv.org/abs/2605.18364][arXiv]]
- G. Lauga, and S. Vaiter. *Characterizations of inexact proximal operators.* /Preprint./ [[https://arxiv.org/abs/2602.02022][arXiv]]

* 2025

- B. Pascal, and S. Vaiter. *Risk Estimate under a Nonstationary Autoregressive Model for Data-Driven Reproduction Number Estimation.* /Signal Processing./ [[https://doi.org/10.1016/j.sigpro.2025.110246][DOI]] [[https://arxiv.org/abs/2409.14937][arXiv]]
- J. Bolte, T. Lê, E. Pauwels, and S. Vaiter. *Geometric and computational hardness of bilevel programming.* /Mathematical Programming./ [[https://doi.org/10.1007/s10107-025-02229-w][DOI]] [[https://arxiv.org/abs/2407.12372][arXiv]]
- R. Kawata, Y. Song, A. Bietti, N. Nishikawa, T. Suzuki, S. Vaiter, and D. Wu. *From Shortcut to Induction Head: How Data Diversity Shapes Algorithm Selection in Transformers.* /Advances in Neural Information Processing Systems (NeurIPS)./ [[https://arxiv.org/abs/2512.18634][arXiv]]
- F. E. Khoury, E. Pauwels, S. Vaiter, and M. Arbel. *Learning Theory for Kernel Bilevel Optimization.* /Advances in Neural Information Processing Systems (NeurIPS)./ [[https://arxiv.org/abs/2502.08457][arXiv]]
- L. Chapel, R. Tavenard, and S. Vaiter. *Differentiable Generalized Sliced Wasserstein Plans.* /Advances in Neural Information Processing Systems (NeurIPS)./ [[https://arxiv.org/abs/2505.22049][arXiv]]
- R. Chhaibi, S. Gratton, and S. Vaiter. *Faster Computation of Entropic Optimal Transport via Stable Low Frequency Modes.* /Preprint./ [[https://arxiv.org/abs/2506.14780][arXiv]]

* 2024

- Y. Traonmilin, R. Gribonval, and S. Vaiter. *A theory of optimal convex regularization for low-dimensional recovery.* /Information and Inference: A Journal of the IMA./ [[https://arxiv.org/abs/2112.03540][arXiv]]
- Q. Klopfenstein, Q. Bertrand, A. Gramfort, J. Salmon, and S. Vaiter. *Model identification and local linear convergence of coordinate descent.* /Optimization Letters./ [[https://arxiv.org/abs/2010.11825][arXiv]]
- H. Ghanem, S. Vaiter, and N. Keriven. *Gradient Scarcity with Bilevel Optimization for Graph Learning.* /Transactions on Machine Learning Research./ [[https://arxiv.org/abs/2303.13964][arXiv]]
- M. Cordonnier, N. Keriven, N. Tremblay, and S. Vaiter. *Convergence of Message Passing Graph Neural Networks with Generic Aggregation On Large Random Graphs.* /Journal of Machine Learning Research./ [[https://arxiv.org/abs/2304.11140][arXiv]]
- S. Jaffard, S. Vaiter, A. Muzy, and P. Reynaud-Bouret. *Provable local learning rule by expert aggregation for a Hawkes network.* /International Conference on Artificial Intelligence and Statistics (AISTATS)./ [[https://files.samuelvaiter.com/papers/jaffard2024provable.pdf][PDF]] [[https://arxiv.org/abs/2304.08061][arXiv]]
- F. Iutzeler, E. Pauwels, and S. Vaiter. *Derivatives of Stochastic Gradient Descent in parametric optimization.* /Advances in Neural Information Processing Systems (NeurIPS)./ [[https://arxiv.org/abs/2405.15894][arXiv]]
- M. Dagréou, T. Moreau, S. Vaiter, and P. Ablin. *A Near-Optimal Algorithm for Bilevel Empirical Risk Minimization.* /International Conference on Artificial Intelligence and Statistics (AISTATS)./ [[https://files.samuelvaiter.com/papers/dagreou2024near.pdf][PDF]] [[https://arxiv.org/abs/2302.08766][arXiv]]
- M. Dagréou, P. Ablin, S. Vaiter, and T. Moreau. *How to compute Hessian-vector products?.* /International Conference on Learning Representations (ICLR) Blogposts Track./

* 2023

- E. Pauwels, and S. Vaiter. *The Derivatives of Sinkhorn-Knopp Converge.* /SIAM Journal on Optimization./ [[https://doi.org/10.1137/22M1512703][DOI]] [[https://files.samuelvaiter.com/papers/pauwels2023derivatives.pdf][PDF]] [[https://arxiv.org/abs/2207.12717][arXiv]]
- H. Ghanem, J. Salmon, N. Keriven, and S. Vaiter. *Supervised learning of analysis-sparsity priors with automatic differentiation.* /IEEE Signal Processing Letters./ [[https://doi.org/10.1109/LSP.2023.3244511][DOI]] [[https://arxiv.org/abs/2112.07990][arXiv]]
- X. Dupuis, and S. Vaiter. *The Geometry of Sparse Analysis Regularization.* /SIAM Journal on Optimization./ [[https://doi.org/10.1137/19M1271877][DOI]] [[https://files.samuelvaiter.com/papers/dupuis2023geometry.pdf][PDF]] [[https://arxiv.org/abs/1907.01769][arXiv]] [[https://hal.science/hal-02169356][HAL]]
- N. Keriven, and S. Vaiter. *What functions can Graph Neural Networks compute on random graphs? The role of Positional Encoding.* /Advances in Neural Information Processing Systems (NeurIPS)./ [[https://files.samuelvaiter.com/papers/keriven2023what.pdf][PDF]] [[https://arxiv.org/abs/2305.14814][arXiv]]
- R. Catellier, S. Vaiter, and D. Garreau. *On the Robustness of Text Vectorizers.* /International Conference on Machine Learning (ICML)./ [[https://arxiv.org/abs/2303.07203][arXiv]]
- J. Bolte, E. Pauwels, and S. Vaiter. *One-step differentiation of iterative algorithms.* /Advances in Neural Information Processing Systems (NeurIPS)./ [[https://files.samuelvaiter.com/papers/bolte2023one.pdf][PDF]] [[https://arxiv.org/abs/2305.13768][arXiv]]
- M. Dagréou, T. Moreau, S. Vaiter, and P. Ablin. *Borne inférieure de compléxité et algorithme quasi-optimal pour la minimisation de risque empirique bi-niveaux.* /Colloque Francophone de Traitement du Signal et des Images (GRETSI)./
- M. Cordonnier, N. Keriven, N. Tremblay, and S. Vaiter. *Convergence of Message Passing Graph Neural Networks with Generic Aggregation on Random Graphs.* /Colloque Francophone de Traitement du Signal et des Images (GRETSI)./
- M. Cordonnier, N. Keriven, N. Tremblay, and S. Vaiter. *Convergence of Message Passing Graph Neural Networks with Generic Aggregation on Random Graphs.* /Graph Signal Processing workshop./

* 2022

- N. Keriven, and S. Vaiter. *Sparse and Smooth: improved guarantees for Spectral Clustering in the Dynamic Stochastic Block Model.* /Electronic Journal of Statistics./ [[https://doi.org/10.1214/22-EJS1986][DOI]] [[https://files.samuelvaiter.com/papers/keriven2022dsbm.pdf][PDF]] [[https://arxiv.org/abs/2002.02892][arXiv]] [[https://hal.science/hal-02484970][HAL]]
- Q. Bertrand, Q. Klopfenstein, M. Massias, M. Blondel, S. Vaiter, A. Gramfort, and J. Salmon. *Implicit differentiation for fast hyperparameter selection in non-smooth convex learning.* /Journal of Machine Learning Research./ [[https://files.samuelvaiter.com/papers/bertrand2022implicit.pdf][PDF]] [[https://arxiv.org/abs/2105.01637][arXiv]]
- T. Moreau, M. Massias, A. Gramfort, P. Ablin, P.-A. Bannier, B. Charlier, M. Dagréou, T. D. l. Tour, G. Durif, C. F. Dantas, Q. Klopfenstein, J. Larsson, E. Lai, T. Lefort, M. Malezieu, B. Moufad, B. T. Nguyen, A. Rakotomamonjy, Z. Ramzie, J. Salmon, and S. Vaiter. *Benchopt: Reproducible, efficient and collaborative optimization benchmarks.* /Advances in Neural Information Processing Systems (NeurIPS)./ [[https://files.samuelvaiter.com/papers/moreau2022benchopt.pdf][PDF]] [[https://arxiv.org/abs/2206.13424][arXiv]]
- M. Dagréou, P. Ablin, S. Vaiter, and T. Moreau. *A framework for bilevel optimization that enables stochastic and global variance reduction algorithms.* /Advances in Neural Information Processing Systems (NeurIPS)./ [[https://arxiv.org/abs/2201.13409][arXiv]]
- J. Bolte, E. Pauwels, and S. Vaiter. *Automatic differentiation of nonsmooth iterative algorithms.* /Advances in Neural Information Processing Systems (NeurIPS)./ [[https://files.samuelvaiter.com/papers/bolte2022automatic.pdf][PDF]] [[https://arxiv.org/abs/2206.00457][arXiv]]
- M. Dagréou, P. Ablin, S. Vaiter, and T. Moreau. *Algorithmes stochastiques et réduction de variance grâce à un nouveau cadre pour l’optimisation bi-niveaux.* /Colloque Francophone de Traitement du Signal et des Images (GRETSI)./

* 2021

- B. Pascal, S. Vaiter, N. Pustelnik, and P. Abry. *Automated data-driven selection of the hyperparameters for Total-Variation based texture segmentation.* /Journal of Mathematical Imaging and Vision./ [[https://files.samuelvaiter.com/papers/pascal2021automated.pdf][PDF]] [[https://arxiv.org/abs/2004.09434][arXiv]]
- Q. Klopfenstein, and S. Vaiter. *Linear Support Vector Regression with Linear Constraints.* /Machine Learning./ [[https://doi.org/10.1007/s10994-021-06018-2][DOI]] [[https://arxiv.org/abs/1911.02306][arXiv]] [[https://hal.science/hal-02349160][HAL]]
- C.-A. Deledalle, N. Papadakis, J. Salmon, and S. Vaiter. *Block based refitting in ℓ₁₂ sparse regularisation.* /Journal of Mathematical Imaging and Vision./ [[https://doi.org/10.1007/s10851-020-00993-2][DOI]] [[https://files.samuelvaiter.com/papers/deledalle2021block.pdf][PDF]] [[https://arxiv.org/abs/1910.11186][arXiv]] [[https://hal.science/hal-02330441][HAL]]
- N. Keriven, A. Bietti, and S. Vaiter. *On the Universality of Graph Neural Networks on Large Random Graphs.* /Advances in Neural Information Processing Systems (NeurIPS)./ [[https://arxiv.org/abs/2105.13099][arXiv]]
- S. Vaiter. *From optimization to algorithmic differentiation: a graph detour.* /HDR Thesis./ [[https://files.samuelvaiter.com/papers/vaiter2021hdr.pdf][PDF]]

* 2020

- M. Massias, S. Vaiter, A. Gramfort, and J. Salmon. *Dual Extrapolation for Sparse Generalized Linear Models.* /Journal of Machine Learning Research./ [[https://files.samuelvaiter.com/papers/massias2020dual.pdf][PDF]] [[https://arxiv.org/abs/1907.05830][arXiv]] [[https://hal.science/hal-02263500][HAL]]
- N. Keriven, A. Bietti, and S. Vaiter. *Convergence and Stability of Graph Convolutional Networks on Large Random Graphs.* /Advances in Neural Information Processing Systems (NeurIPS)./ [[https://files.samuelvaiter.com/papers/keriven2020convergence.pdf][PDF]] [[https://arxiv.org/abs/2006.01868][arXiv]]
- Q. Bertrand, Q. Klopfenstein, M. Blondel, S. Vaiter, A. Gramfort, and J. Salmon. *Implicit differentiation of Lasso-type models for hyperparameter optimization.* /International Conference on Machine Learning (ICML)./ [[https://files.samuelvaiter.com/papers/bertrand2020implicit.pdf][PDF]] [[https://arxiv.org/abs/2002.08943][arXiv]]

* 2019

- A. Barbara, A. Jourani, and S. Vaiter. *Maximal Solutions of Sparse Analysis Regularization.* /Journal of Optimization Theory and Applications./ [[https://doi.org/10.1007/s10957-018-1385-3][DOI]] [[https://files.samuelvaiter.com/papers/barbara2019maximal.pdf][PDF]] [[https://arxiv.org/abs/1703.00192][arXiv]] [[https://hal.science/hal-01467965][HAL]]
- C.-A. Deledalle, N. Papadakis, J. Salmon, and S. Vaiter. *Refitting solutions promoted by ℓ₁₂ sparse analysis regularization with block penalties.* /International Conference on Scale Space and Variational Methods in Computer Vision (SSVM)./ [[https://arxiv.org/abs/1903.00741][arXiv]] [[https://hal.science/hal-02059006][HAL]]
- M. Massias, S. Vaiter, A. Gramfort, and J. Salmon. *Exploiting regularity in sparse Generalized Linear Models.* /Signal Processing with Adaptive Sparse Structured Representations (SPARS)./ [[https://hal.science/hal-02288859][HAL]]

* 2018

- S. Vaiter, G. Peyré, and J. Fadili. *Model Consistency of Partly Smooth Regularizers.* /IEEE Transactions on Information Theory./ [[https://doi.org/10.1109/TIT.2017.2713822][DOI]] [[https://files.samuelvaiter.com/papers/vaiter2018model.pdf][PDF]] [[https://arxiv.org/abs/1405.1004][arXiv]] [[https://hal.science/hal-00987293][HAL]]
- Y. Traonmilin, and S. Vaiter. *Optimality of 1-norm regularization among weighted 1-norms for sparse recovery: a case study on how to find optimal regularizations.* /New Computational Methods for Inverse Problems (NCMIP)./ [[https://files.samuelvaiter.com/papers/traonmilin2018optimality.pdf][PDF]] [[https://arxiv.org/abs/1803.00773][arXiv]] [[https://hal.science/hal-01720871][HAL]]
- Y. Traonmilin, S. Vaiter, and R. Gribonval. *Is the 1-norm the best convex sparse regularization?.* /iTWIST./ [[https://files.samuelvaiter.com/papers/traonmilin2018is.pdf][PDF]] [[https://arxiv.org/abs/1806.08690][arXiv]] [[https://hal.science/hal-01819219][HAL]]

* 2017

- S. Vaiter, C.-A. Deledalle, G. Peyré, J. Fadili, and C. Dossal. *The Degrees of Freedom of Partly Smooth Regularizers.* /Annals of the Institute of Statistical Mathematics./ [[https://doi.org/10.1007/s10463-016-0563-z][DOI]] [[https://files.samuelvaiter.com/papers/vaiter2017dof.pdf][PDF]] [[https://arxiv.org/abs/1404.5557][arXiv]] [[https://hal.science/hal-00981634][HAL]]
- C.-A. Deledalle, N. Papadakis, J. Salmon, and S. Vaiter. *CLEAR: Covariant LEAst-square Re-fitting with applications to image restoration.* /SIAM Journal on Imaging Sciences./ [[https://doi.org/10.1137/16M1080318][DOI]] [[https://files.samuelvaiter.com/papers/deledalle2017clear.pdf][PDF]] [[https://arxiv.org/abs/1606.05158][arXiv]] [[https://hal.science/hal-01333295][HAL]]
- A. Chambolle, P. Tan, and S. Vaiter. *Accelerated Alternating Descent Methods for Dykstra-like problems.* /Journal of Mathematical Imaging and Vision./ [[https://doi.org/10.1007/s10851-017-0724-6][DOI]] [[https://files.samuelvaiter.com/papers/chambolle2017accelerated.pdf][PDF]] [[https://hal.science/hal-01346532][HAL]]
- P. Bellec, J. Salmon, and S. Vaiter. *A Sharp Oracle Inequality for Graph-Slope.* /Electronic Journal of Statistics./ [[https://doi.org/10.1214/17-EJS1364][DOI]] [[https://files.samuelvaiter.com/papers/bellec2017sharp.pdf][PDF]] [[https://arxiv.org/abs/1706.06977][arXiv]] [[https://hal.science/hal-01544680][HAL]]
- C.-A. Deledalle, N. Papadakis, J. Salmon, and S. Vaiter. *Characterizing the maximum parameter of the total-variation denoising through the pseudo-inverse of the divergence.* /Signal Processing with Adaptive Sparse Structured Representations (SPARS)./ [[https://files.samuelvaiter.com/papers/deledalle2017characterizing.pdf][PDF]] [[https://arxiv.org/abs/1612.03080][arXiv]] [[https://hal.science/hal-01412059][HAL]]

* 2015

- S. Vaiter, M. Golbabaee, J. Fadili, and G. Peyré. *Model Selection with Low Complexity Priors.* /Information and Inference: A Journal of the IMA./ [[https://doi.org/10.1093/imaiai/iav005][DOI]] [[https://files.samuelvaiter.com/papers/vaiter2015model.pdf][PDF]] [[https://arxiv.org/abs/1307.2342][arXiv]] [[https://hal.science/hal-00842603][HAL]]
- S. Vaiter, G. Peyré, and J. Fadili. *Low Complexity Regularization of Linear Inverse Problems.* /Book chapter in Sampling Theory, a Renaissance./ [[https://doi.org/10.1007/978-3-319-19749-4][DOI]] [[https://files.samuelvaiter.com/papers/vaiter2015low.pdf][PDF]] [[https://arxiv.org/abs/1407.1598][arXiv]] [[https://hal.science/hal-01018927][HAL]]

* 2014

- C.-A. Deledalle, S. Vaiter, J. Fadili, and G. Peyré. *Stein Unbiased GrAdient estimator of the Risk (SUGAR) for multiple parameter selection.* /SIAM Journal on Imaging Sciences./ [[https://doi.org/10.1137/140968045][DOI]] [[https://files.samuelvaiter.com/papers/deledalle2014sugar.pdf][PDF]] [[https://arxiv.org/abs/1405.1164][arXiv]] [[https://hal.science/hal-00987295][HAL]]
- S. Vaiter. *Low Complexity Regularizations of Inverse Problems.* /PhD Thesis./ [[https://files.samuelvaiter.com/papers/vaiter2014phd.pdf][PDF]] [[/publications/vaiter2014phd/][SITE]]

* 2013

- S. Vaiter, G. Peyré, C. Dossal, and J. Fadili. *Robust Sparse Analysis Regularization.* /IEEE Transactions on Information Theory./ [[https://doi.org/10.1109/TIT.2012.2233859][DOI]] [[https://files.samuelvaiter.com/papers/vaiter2013robust.pdf][PDF]] [[https://arxiv.org/abs/1109.6222][arXiv]] [[https://hal.science/hal-00627452][HAL]]
- S. Vaiter, C.-A. Deledalle, G. Peyré, C. Dossal, and J. Fadili. *Local Behavior of Sparse Analysis Regularization: Applications to Risk Estimation.* /Applied and Computational Harmonic Analysis./ [[https://doi.org/10.1016/j.acha.2012.11.006][DOI]] [[https://files.samuelvaiter.com/papers/vaiter2013local.pdf][PDF]] [[https://arxiv.org/abs/1204.3212][arXiv]] [[https://hal.science/hal-00687751][HAL]]
- S. Vaiter, G. Peyré, and J. Fadili. *Robust Polyhedral Regularization.* /SAMPTA./ [[https://files.samuelvaiter.com/papers/vaiter2013polyhedral.pdf][PDF]] [[https://arxiv.org/abs/1304.6033][arXiv]] [[https://hal.science/hal-00816377][HAL]]
- J. Fadili, G. Peyré, S. Vaiter, C.-A. Deledalle, and J. Salmon. *Stable Recovery with Analysis Decomposable Priors.* /SAMPTA./ [[https://files.samuelvaiter.com/papers/fadili2013stableb.pdf][PDF]] [[https://arxiv.org/abs/1304.4407][arXiv]]
- S. Vaiter, G. Peyré, and J. Fadili. *Robustesse au bruit des régularisations polyhédrales.* /Colloque Francophone de Traitement du Signal et des Images (GRETSI)./
- J. Fadili, G. Peyré, S. Vaiter, C.-A. Deledalle, and J. Salmon. *Reconstruction Stable par Régularisation Décomposable Analyse.* /Colloque Francophone de Traitement du Signal et des Images (GRETSI)./
- S. Vaiter, G. Peyré, J. Fadili, C.-A. Deledalle, and C. Dossal. *The degrees of freedom of the group Lasso for a general design.* /Signal Processing with Adaptive Sparse Structured Representations (SPARS)./ [[https://files.samuelvaiter.com/papers/vaiter2013dof.pdf][PDF]] [[https://hal.science/hal-00926929][HAL]]

* 2012

- C.-A. Deledalle, S. Vaiter, G. Peyré, J. Fadili, and C. Dossal. *Unbiased Risk Estimation for Sparse Analysis Regularization.* /International Conference on Image Processing (ICIP)./ [[https://doi.org/10.1109/ICIP.2012.6467544][DOI]] [[https://files.samuelvaiter.com/papers/deledalle2012unbiased.pdf][PDF]] [[https://hal.science/hal-00662718][HAL]]
- C.-A. Deledalle, S. Vaiter, G. Peyré, J. Fadili, and C. Dossal. *Proximal Splitting Derivatives for Risk Estimation.* /New Computational Methods for Inverse Problems (NCMIP)./ [[https://doi.org/10.1088/1742-6596/386/1/012003][DOI]] [[https://files.samuelvaiter.com/papers/deledalle2012proximal.pdf][PDF]] [[https://hal.science/hal-0670213][HAL]]
- S. Vaiter, C.-A. Deledalle, G. Peyré, J. Fadili, and C. Dossal. *The Degrees of Freedom of the Group Lasso.* /International Conference on Machine Learning (ICML) Workshop Sparsity, Dictionaries and Projections in Machine Learning and Signal Processing./ [[https://files.samuelvaiter.com/papers/vaiter2012dof.pdf][PDF]] [[https://arxiv.org/abs/1205.1481][arXiv]] [[https://hal.science/hal-00695292][HAL]]
- C.-A. Deledalle, S. Vaiter, G. Peyré, J. Fadili, and C. Dossal. *Risk estimation for matrix recovery with spectral regularization.* /International Conference on Machine Learning (ICML) Workshop Sparsity, Dictionaries and Projections in Machine Learning and Signal Processing./ [[https://files.samuelvaiter.com/papers/deledalle2012risk.pdf][PDF]] [[https://arxiv.org/abs/1205.1482][arXiv]] [[https://hal.science/hal-00695326][HAL]]