2026-05-04, 09:32 CEST Our work "[Towards Understanding Steering Strength](https://arxiv.org/abs/2602.02712)" with Magamed and Damien was accepted to ICML 2026! --- 2026-01-28 #NEWS With the ICML 2026 deadline, I forgot to mention that together with [Sofiane Tanji](https://sofianetanji.com/) and [Yassine Laguel](https://yassine-laguel.github.io/), we have a new preprint [Fairness-informed Pareto Optimization: An Efficient Bilevel Framework](https://arxiv.org/abs/2601.13448). If you like fairness or multiobjective optimization or bilevel optimization, you won't be disappointed to skim it! --- 2026-01-28 A small Rust tool to monitor new email using IMAP IDLE command [svaiter/imapidle_then](https://github.com/svaiter/imapidle_then) --- 2025-12-02 #NEWS **NeurIPS 2025 San Diego**. I will be in San Diego for NeurIPS (December 2-6). --- 2025-11-13 #NEWS **PhD defense: Léo Davy**. Léo Davy defended his PhD thesis (supervisors: Nelly Pustelnik and Patrice Abry) that I had the pleasure to review. Congrats! --- 2025-11-06 #NEWS **Talk at Séminaire Math-IA Bordeaux**. I gave a talk at the Séminaire Math-IA in Bordeaux on [Geometrical and computational complexity of bilevel optimization](https://www.math.u-bordeaux.fr/fr/agenda/7421). --- 2025-10-01 #NEWS **Promoted Directeur de recherche**. Starting today, I am officially promoted [*Directeur de recherche*](https://fr.wikipedia.org/wiki/Directeur_de_recherche_au_CNRS) at CNRS. --- 2025-10-01 #NEWS **CIRM workshop on inverse problems**. I am the CIRM this week for the [(Blind) inverse problems in imaging: from foundations to applications](https://conferences.cirm-math.fr/3349.html) workshop organized by Luca, Emmanuel and Pierre. --- 2025-09-03 #NEWS **New PhD student: Tùng Nguyễn Thanh**. Tùng Nguyễn Thanh just started his PhD with Yassine Laguel and myself. --- 2025-08-11 #NEWS **Workshop at Simons Institute Berkeley**. I am in Berkeley this week for the [Graph Learning Meets Theoretical Computer Science](https://simons.berkeley.edu/workshops/graph-learning-meets-theoretical-computer-science) workshop at the [Simons Institute for the Theory of Computing](https://simons.berkeley.edu/homepage). --- 2025-07-14 #NEWS **Visiting Rennes**. I am visiting [Nicolas Keriven](https://nkeriven.github.io) in Rennes this week. --- 2025-07-07 #NEWS **PhD defense: Sophie Jaffard**. Sophie Jaffard defended his PhD thesis on [Spiking neural networks : learning as point processes](https://theses.hal.science/tel-05290040v1). Congrats to her! It was a pleasure to supervise her with [Patricia Reynaud-Bouret](https://math.univ-cotedazur.fr/~reynaudb). --- 2025-05-20 #NEWS **Café Calcul presentation**. I present at [Café calcul](https://groupe-calcul.cnrs.fr/cafe-ad.html) from Groupe Calcul. I introduce automatic differentiation: from the chain rule and Jacobians to forward and reverse modes (backprop) via computational graphs, showing simple implementations, semantic interpretations, and a glimpse of theory for iterative algorithms. --- 2025-04-29 #NEWS **Talk at LJAD-MAASAI seminar**. I gave a talk at the joint seminar between the Probability and Statistics team of the LJAD and the Inria MASAAI team on some advances on nonconvex bilevel optimization. --- 2025-04-17 #NEWS **Talk at MaLGa Genoa**. I gave a talk at MaLGa in Genoa, hosted by L. Calatroni. --- 2025-04-01 #NEWS **Bilevel paper accepted to Math. Prog.**. Our paper [Geometric and computational hardness of bilevel programming](https://arxiv.org/abs/2407.12372) has been accepted to Math. Prog! --- 2025-03-24 #NEWS **Talk at GDR IASIS Lyon**. I give a talk at GDR IASIS day on bilevel optimization in Lyon. --- 2025-02-02 #NEWS **Oberwolfach workshop**. I was in Oberwolfach for the Mathematical Imaging and Surface Processing workshop. The [report](https://publications.mfo.de/handle/mfo/4228) is available. --- 2025-01-29 #NEWS **Winter school Dijon-Besançon**. I gave a 5-hours introduction to language models at the Winter school Dijon-Besaçon. --- 2025-01-13 #NEWS **MIA 2025 Conference**. We organized [MIA 2025 Conference](https://rt-maiages.math.cnrs.fr/mia25/mia25/) in Paris. --- 2024-12-16 #NEWS **ICSDS 2024 Conference**. We organized the [ICSDS 2024 Conference](https://www.ims-icsds2024.org/home) in Nice. --- 2024-12-10 #NEWS **NeurIPS 2024 Vancouver**. I will be in Vancouver for NeurIPS. --- 2024-12-03 #NEWS **PhD defense: Matthieu Cordonnier**. Matthieu Cordonnier defended his PhD thesis on "Neural networks on large scale random graphs". Congrats! --- 2024-11-28 #NEWS **Talk at SophIA Summit**. I gave an invited talk at [SophIA Summit](https://univ-cotedazur.eu/events/sophia-summit) --- 2024-11-07 #NEWS **MPGNN paper accepted to JMLR**. Our paper [Convergence of Message Passing Graph Neural Networks with Generic Aggregation On Large Random Graphs](https://arxiv.org/abs/2304.11140) was accepted for publication in J. Mach. Learn. Res. --- 2024-10-08 #NEWS **PhD defense: Mathieu Dagréou**. [Mathieu Dagréou](https://matdag.github.io) defended his PhD thesis on "Contributions to stochastic bilevel optimization". Congratulations Mathieu! --- 2024-09-26 #NEWS **Derivatives of SGD accepted to NeurIPS 2024**. Our (w/ F. Iutzeler & E. Pauwels) paper [Derivatives of Stochastic Gradient Descent](https://arxiv.org/abs/2405.15894) was accepted to NeurIPS 2024. --- 2024-09-26 #NEWS **3IA chair holder**. Just learned that I will be a 3IA chair holder for the next 4 years for my project BOGL (Bilevel Optimization for Graph Learning). --- 2024-09-23 #NEWS **LOCA workshop**. We organized with L. Calatroni the [LOCA workshop](https://optazur.github.io/loca2024/) in Sophie-Antipolis. --- 2024-09-10 #NEWS **Talk at SPARNP conference**. I gave a talk at the [Statistical and Probabilistic Analysis of Random Networks and Processes](https://stamford.uni.lu/events/) conference. --- 2024-09-02 #NEWS **One Piece of Math a Day**. Started my tweet serie "One Piece of Math a Day" on [Twitter](https://x.com/vaiter). Also available on my website [here](/one-piece/). --- 2024-07-09 #NEWS **Talk at Inria Grenoble**. I gave a talk at Inria Grenoble on automatic differentiation. --- 2024-07-01 #NEWS **Talk at EURO 2024**. Attending [EURO 2024](https://euro2024cph.dk). I will give an invited talk in the "Algorithms for machine learning and inverse problems" session. --- 2024-06-27 #NEWS **ANR MAD grant accepted**. The grant [ANR MAD](/grants/mad/) was just accepted. I will be the PI of the project "Mathematics of Automatic Differentiation" for the next 4 years with the following consortium: J. Bolte, S. Gadat, E. Pauwels (Toulouse School of Economics), G. Fort, F. Iutzeler (Université Paul Sabatier) and J.-B. Caillau, Y. Laguel (Université Côte d'Azur). --- 2024-06-23 #NEWS **Visiting MILA**. Visiting [G. Gidel](https://gauthiergidel.github.io) at [MILA](https://mila.quebec). I gave a talk at [MTL Opt](https://mtl-mlopt.github.io). --- 2024-06-15 #NEWS **Gradient Scarcity accepted to TMLR**. Accepted paper to TMLR with Hashem Ghanem and Nicolas Keriven [Gradient Scarcity with Bilevel Optimization for Graph Learning](https://openreview.net/forum?id=10YJTIsVYq) with Featured Certification! --- 2024-05-28 #NEWS **Preprint: CHANI**. New preprint with Sophie Jaffard and Patricia Reynaud-Bouret [CHANI: Correlation-based Hawkes Aggregation of Neurons with bio-Inspiration](https://arxiv.org/abs/2405.18828). --- 2024-05-21 #NEWS **Preprint: Derivatives of SGD**. New preprint with Franck Iutzeler and Edouard Pauwels on the [Derivatives of Stochastic Gradient Descent](https://arxiv.org/abs/2405.15894). --- 2024-04-09 #NEWS **HVP blogpost spotlight at ICLR 2024**. Our blogpost with Mathieu Dagréou, Pierre Ablin and Thomas Moreau [How to compute Hessian-vector products?](https://iclr-blogposts.github.io/2024/blog/bench-hvp/) was accepted to ICLR 2024 as *spotlight*. --- 2024-03-01 #NEWS **Visiting Flatiron Institute NYC**. Visiting [A. Bietti](https://alberto.bietti.me) at [CCM, Flatiron Institute, NYC](https://www.simonsfoundation.org/flatiron/center-for-computational-mathematics/). I presented our work on iterative automatic differentiation. --- 2024-01-24 #NEWS **Talk at PEPR PDE-AI kickoff**. Talk at the kickoff meeting of the [PEPR PDE-AI](https://pde-ai.math.cnrs.fr/) project. --- 2024-01-20 #NEWS **Two papers accepted to AISTATS 2024**. Our papers [Provable local learning rule by expert aggregation for a Hawkes network](https://arxiv.org/abs/2304.08061) and [A Lower Bound and a Near-Optimal Algorithm for Bilevel Empirical Risk Minimization](https://arxiv.org/abs/2302.08766) were accepted to AISTATS 2024. --- 2017-10-24 #NEWS **Graph-Slope paper accepted in EJS**. Our paper with [Pierre C. Bellec](http://www.stat.rutgers.edu/home/PCB71/) and [Joseph Salmon](http://josephsalmon.eu) coined [A sharp oracle inequality for Graph-Slope](https://arxiv.org/abs/1706.06977) has been accepted in Electronic Journal of Statistics. --- 2017-06-21 #NEWS **Preprint on Graph-Slope**. Together with [Pierre C. Bellec](http://www.stat.rutgers.edu/home/PCB71/) and [Joseph Salmon](http://josephsalmon.eu), we released our preprint [A sharp oracle inequality for Graph-Slope](https://arxiv.org/abs/1706.06977). --- 2017-04-16 #NEWS **Model Consistency of Partly Smooth Regularizers accepted in TIT**. After two long years in review, our paper with J. Fadili and G. Peyré [Model Consistency of Partly Smooth Regularizers](http://hal.archives-ouvertes.fr/hal-00987293) has been accepted for publication in IEEE Transactions on Information Theory. --- 2017-03-20 #NEWS **Accelerated alternating descent methods published in JMIV**. Our paper with A. Chambolle and P. Tan, [Accelerated Alternating Descent Methods for Dykstra-like problems](https://hal.archives-ouvertes.fr/hal-01346532) has been accepted for publication in Journal of Mathematical Imaging and Vision. The online first version is available [here](http://link.springer.com/article/10.1007/s10851-017-0724-6). --- 2017-02-14 #NEWS **New preprint on non-uniqueness for the analysis Lasso**. Our work with A. Barbara and A. Jourani on non-uniqueness for the analysis Lasso is available at the following link [Maximal solutions of sparse analysis regularization](https://hal.archives-ouvertes.fr/hal-01467965). --- 2016-12-03 #NEWS **CLEAR accepted in SIAM IS**. Our paper on re-fitting has been accepted for publication in SIAM Journal on Imaging Science. The preprint is available at the following link [CLEAR: Covariant LEAst-square Re-fitting with applications to image restoration](https://arxiv.org/abs/1606.05158). --- 2016-07-22 #NEWS **New preprint on accelerated alternating descent methods**. Together with A. Chambolle and P. Tan, we extended recent results by Antonin and T. Pock on the acceleration of alternating minimization techniques for quadratic plus nons-mooth objectives depending on two variables, with an emphasis on the strongly convex case. The paper is available at [Accelerated Alternating Descent Methods for Dykstra-like problems](https://hal.archives-ouvertes.fr/hal-01346532). --- 2016-06-16 #NEWS **New preprint on re-fitting**. Together with C. Deledalle, N. Papadakis and J. Salmon, we proposed a new framework to remove parts of the systematic errors affecting popular restoration algorithms. This work is available at the following link [CLEAR: Covariant LEAst-square Re-fitting with applications to image restoration](https://arxiv.org/abs/1606.05158). --- 2016-04-01 #NEWS **Paper accepted**. Our paper [The Degrees of Freedom of Partly Smooth Regularizers](http://hal.archives-ouvertes.fr/hal-00981634) has been accepted for publication in Annals of the Institute of Statistical Mathematics (AISM). --- 2015-11-03 #NEWS **MOA Workshop 2015**. We organize at the [IMB](http://math.u-bourgogne.fr/) the annual workshop of the [GdR MOA](http://gdrmoa.math.cnrs.fr/) in December 2015. It will highlight recent advances in optimization. More information [here](/events/journees-moa-2015). --- 2015-10-28 #NEWS **PhD PGMO award**. I received one of the two PGMO PhD award for my thesis. This award is delivered by [Programme Gaspard Monge pour l'optimisation et la recherche opérationnelle](http://www.fondation-hadamard.fr/pgmo.php?url=95.142.164.215/fr/prixthese). --- 2015-10-01 #NEWS **CNRS**. My postdoctoral position is over and I am now a CNRS researcher (CR2). I joined the [IMB](http://math.u-bourgogne.fr/) at [Université de Bourgogne](http://www.u-bourgogne.fr/). --- 2015-04-02 #NEWS **PhD award**. I received a best PhD award for my thesis. This award is delivered by [Fondation Dauphine](http://www.fondation.dauphine.fr/). --- 2015-01-12 #NEWS **Two new papers**. Our paper [Model Selection with Low Complexity Priors](http://hal.archives-ouvertes.fr/hal-00842603) has been accepted for publication Information and Inference (IMAIAI). Moreover, our book chapter [Low Complexity Regularization of Linear Inverse Problems](http://hal.archives-ouvertes.fr/hal-01018927) will be published in *Sampling Theory, a Renaissance* edited by G. Pfander. --- 2014-10-01 #NEWS **New Position**. I just started my postdoc with [Antonin Chambolle](http://www.cmap.polytechnique.fr/~antonin/) at the CMAP, Ecole Polytechnique. --- 2014-08-19 #NEWS **SUGAR**. Our paper [Stein Unbiased GrAdient estimator of the Risk (SUGAR) for multiple parameter selection](http://hal.archives-ouvertes.fr/hal-00987295) has been accepted for publication in [SIAM Journal on Imaging Sciences](http://www.siam.org/journals/siims.php). --- 2014-07-10 #NEWS **Ph. D.**. I successfully defended my PhD dissertation, see [this page](http://samuelvaiter.com/phd/) for more information. --- 2014-05-05 #NEWS **Preprints on Model Stability and Stein Estimation**. [Model Consistency of Partly Smooth Regularizers](http://hal.archives-ouvertes.fr/hal-00987293) and [Stein Unbiased GrAdient estimator of the Risk (SUGAR) for multiple parameter selection](http://hal.archives-ouvertes.fr/hal-00987295) are now available online. --- 2014-04-22 #NEWS **Preprint DOF**. Our last preprint [The Degrees of Freedom of Partly Smooth Regularizers](http://hal.archives-ouvertes.fr/hal-00981634) is available online.