#+title: News
#+date: 2026-10-22
#+status: in progress
#+layout: news

# One entry per heading, newest first, titled by an inactive timestamp:
# "* [2026-05-04 Mon 09:32]" (time optional). An entry's anchor is its
# date and time (#2026-05-04-0932).

* [2026-11-04 Wed]
*arXivScan*. I just deployed a refined version of [[https://arxivscan.samuelvaiter.com/][arXivScan]]. Source code available on [[https://github.com/svaiter/arxivscan][GitHub]].

* [2026-09-21 Mon]
*GraphLearn 2 at CIRM*. With [[https://nkeriven.github.io][Nicolas Keriven]] and [[http://cmatias.perso.math.cnrs.fr][Catherine Matias]], we organize GraphLearn, second edition, at CIRM, Marseille (September 21–25).

* [2026-07-06 Mon]
*ICML 2026 Seoul*. I am in Seoul for ICML 2026.

* [2026-06-24 Wed]
*Prix Neveu for Sophie Jaffard*. Our former PhD student [[https://sites.google.com/view/sophiejaffard/accueil][Sophie Jaffard]] is the laureate of the [[https://fr.wikipedia.org/wiki/Jacques_Neveu][Jacques Neveu prize]]!

* [2026-05-18 Mon]
*Preprint: Proximal basin hopping*. New preprint with Guillaume Lauga and Cesare Molinari, "[[https://arxiv.org/abs/2605.18364][Proximal basin hopping: global optimization with guarantees]]".

* [2026-05-15 Fri]
*DEQ paper accepted to SIIMS*. Our paper with Christian Daniele, Silvia Villa and Luca Calatroni, "[[https://doi.org/10.1137/25M1779048][Deep Equilibrium models for Poisson Imaging Inverse problems via Mirror Descent]]", is published in SIAM J. Imaging Sciences.

* [2026-05-07 Thu]
*Preprint: On the Hardness of Junking LLMs*. New preprint with Marco Rando, "[[https://arxiv.org/abs/2605.05116][On the Hardness of Junking LLMs]]".

* [2026-05-04 Mon]
Our work "[[https://arxiv.org/abs/2602.02712][Towards Understanding Steering Strength]]" with Magamed and Damien was accepted to ICML 2026!

* [2026-04-15 Wed]
*Bilevel paper accepted to MOR*. "[[https://doi.org/10.1287/moor.2025.0914][Bilevel gradient methods and Morse parametric qualification]]" with Jérôme Bolte, Tùng Lê and Edouard Pauwels is published in Mathematics of Operations Research.

* [2026-03-16 Mon]
*SMAI-MODE 2026 in Nice*. We host the Journées SMAI-MODE 2026 at LJAD, starting with mini-courses by Aymeric Dieuleveut and Adrien Taylor.

* [2026-03-02 Mon]
*CHANI accepted to JMLR*. Our paper with Sophie Jaffard and [[https://math.univ-cotedazur.fr/~reynaudb][Patricia Reynaud-Bouret]], "[[https://arxiv.org/abs/2405.18828][CHANI: Correlation-based Hawkes Aggregation of Neurons with bio-Inspiration]]", was accepted to J. Mach. Learn. Res.

* [2026-02-02 Mon]
*Preprint: Inexact proximal operators*. New preprint with Guillaume Lauga, "[[https://arxiv.org/abs/2602.02022][Characterizations of inexact proximal operators]]".

* [2026-01-30 Fri]
*Preprint: ZOBA*. New preprint with Marco Rando, "[[https://arxiv.org/abs/2601.21836][ZOBA: An Efficient Single-loop Zeroth-order Bilevel Optimization Algorithm]]".

* [2026-01-28 Wed]
With the ICML 2026 deadline, I forgot to mention that together with [[https://sofianetanji.com/][Sofiane Tanji]] and [[https://yassine-laguel.github.io/][Yassine Laguel]], we have a new preprint [[https://arxiv.org/abs/2601.13448][Fairness-informed Pareto Optimization: An Efficient Bilevel Framework]]. If you like fairness or multiobjective optimization or bilevel optimization, you won't be disappointed to skim it!

* [2026-01-28 Wed]
A small Rust tool to monitor new email using IMAP IDLE command [[https://github.com/svaiter/imapidle_then][svaiter/imapidle_then]]

* [2025-12-02 Tue]
*NeurIPS 2025 San Diego*. I will be in San Diego for NeurIPS (December 2-6).

* [2025-11-13 Thu]
*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 Thu]
*Talk at Séminaire Math-IA Bordeaux*. I gave a talk at the Séminaire Math-IA in Bordeaux on [[https://www.math.u-bordeaux.fr/fr/agenda/7421][Geometrical and computational complexity of bilevel optimization]].

* [2025-10-01 Wed]
*Promoted Directeur de recherche*. Starting today, I am officially promoted [[https://fr.wikipedia.org/wiki/Directeur_de_recherche_au_CNRS][/Directeur de recherche/]] at CNRS.

* [2025-10-01 Wed]
*CIRM workshop on inverse problems*. I am at the CIRM this week for the [[https://conferences.cirm-math.fr/3349.html][(Blind) inverse problems in imaging: from foundations to applications]] workshop organized by Luca, Emmanuel and Pierre.

* [2025-09-03 Wed]
*New PhD student: Tùng Nguyễn Thanh*. Tùng Nguyễn Thanh just started his PhD with Yassine Laguel and myself.

* [2025-08-11 Mon]
*Workshop at Simons Institute Berkeley*. I am in Berkeley this week for the [[https://simons.berkeley.edu/workshops/graph-learning-meets-theoretical-computer-science][Graph Learning Meets Theoretical Computer Science]] workshop at the [[https://simons.berkeley.edu/homepage][Simons Institute for the Theory of Computing]].

* [2025-07-14 Mon]
*Visiting Rennes*. I am visiting [[https://nkeriven.github.io][Nicolas Keriven]] in Rennes this week.

* [2025-07-07 Mon]
*PhD defense: Sophie Jaffard*. Sophie Jaffard defended his PhD thesis on [[https://theses.hal.science/tel-05290040v1][Spiking neural networks : learning as point processes]]. Congrats to her! It was a pleasure to supervise her with [[https://math.univ-cotedazur.fr/~reynaudb][Patricia Reynaud-Bouret]].

* [2025-05-20 Tue]
*Café Calcul presentation*. I present at [[https://groupe-calcul.cnrs.fr/cafe-ad.html][Café calcul]] 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 Tue]
*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 Thu]
*Talk at MaLGa Genoa*. I gave a talk at MaLGa in Genoa, hosted by L. Calatroni.

* [2025-04-01 Tue]
*Bilevel paper accepted to Math. Prog.*. Our paper [[https://arxiv.org/abs/2407.12372][Geometric and computational hardness of bilevel programming]] has been accepted to Math. Prog!

* [2025-03-24 Mon]
*Talk at GDR IASIS Lyon*. I give a talk at GDR IASIS day on bilevel optimization in Lyon.

* [2025-02-02 Sun]
*Oberwolfach workshop*. I was in Oberwolfach for the Mathematical Imaging and Surface Processing workshop. The [[https://publications.mfo.de/handle/mfo/4228][report]] is available.

* [2025-01-29 Wed]
*Winter school Dijon-Besançon*. I gave a 5-hours introduction to language models at the Winter school Dijon-Besaçon.

* [2025-01-13 Mon]
*MIA 2025 Conference*. We organized [[https://rt-maiages.math.cnrs.fr/mia25/mia25/][MIA 2025 Conference]] in Paris.

* [2024-12-16 Mon]
*ICSDS 2024 Conference*. We organized the [[https://www.ims-icsds2024.org/home][ICSDS 2024 Conference]] in Nice.

* [2024-12-10 Tue]
*NeurIPS 2024 Vancouver*. I will be in Vancouver for NeurIPS.

* [2024-12-03 Tue]
*PhD defense: Matthieu Cordonnier*. Matthieu Cordonnier defended his PhD thesis on "Neural networks on large scale random graphs". Congrats!

* [2024-11-28 Thu]
*Talk at SophIA Summit*. I gave an invited talk at [[https://univ-cotedazur.eu/events/sophia-summit][SophIA Summit]]

* [2024-11-07 Thu]
*MPGNN paper accepted to JMLR*. Our paper [[https://arxiv.org/abs/2304.11140][Convergence of Message Passing Graph Neural Networks with Generic Aggregation On Large Random Graphs]] was accepted for publication in J. Mach. Learn. Res.

* [2024-10-08 Tue]
*PhD defense: Mathieu Dagréou*. [[https://matdag.github.io][Mathieu Dagréou]] defended his PhD thesis on "Contributions to stochastic bilevel optimization". Congratulations Mathieu!

* [2024-09-26 Thu]
*Derivatives of SGD accepted to NeurIPS 2024*. Our (w/ F. Iutzeler & E. Pauwels) paper [[https://arxiv.org/abs/2405.15894][Derivatives of Stochastic Gradient Descent]] was accepted to NeurIPS 2024.

* [2024-09-26 Thu]
*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 Mon]
*LOCA workshop*. We organized with L. Calatroni the [[https://optazur.github.io/loca2024/][LOCA workshop]] in Sophie-Antipolis.

* [2024-09-10 Tue]
*Talk at SPARNP conference*. I gave a talk at the [[https://stamford.uni.lu/events/][Statistical and Probabilistic Analysis of Random Networks and Processes]] conference.

* [2024-09-02 Mon]
*One Piece of Math a Day*. Started my tweet serie "One Piece of Math a Day" on [[https://x.com/vaiter][Twitter]]. Also available on my website [[/one-piece/][here]].

* [2024-07-09 Tue]
*Talk at Inria Grenoble*. I gave a talk at Inria Grenoble on automatic differentiation.

* [2024-07-01 Mon]
*Talk at EURO 2024*. Attending [[https://euro2024cph.dk][EURO 2024]]. I will give an invited talk in the "Algorithms for machine learning and inverse problems" session.

* [2024-06-27 Thu]
*ANR MAD grant accepted*. The grant [[/grants/mad/][ANR 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 Sun]
*Visiting MILA*. Visiting [[https://gauthiergidel.github.io][G. Gidel]] at [[https://mila.quebec][MILA]]. I gave a talk at [[https://mtl-mlopt.github.io][MTL Opt]].

* [2024-06-15 Sat]
*Gradient Scarcity accepted to TMLR*. Accepted paper to TMLR with Hashem Ghanem and Nicolas Keriven [[https://openreview.net/forum?id=10YJTIsVYq][Gradient Scarcity with Bilevel Optimization for Graph Learning]] with Featured Certification!

* [2024-05-28 Tue]
*Preprint: CHANI*. New preprint with Sophie Jaffard and Patricia Reynaud-Bouret [[https://arxiv.org/abs/2405.18828][CHANI: Correlation-based Hawkes Aggregation of Neurons with bio-Inspiration]].

* [2024-05-21 Tue]
*Preprint: Derivatives of SGD*. New preprint with Franck Iutzeler and Edouard Pauwels on the [[https://arxiv.org/abs/2405.15894][Derivatives of Stochastic Gradient Descent]].

* [2024-04-09 Tue]
*HVP blogpost spotlight at ICLR 2024*. Our blogpost with Mathieu Dagréou, Pierre Ablin and Thomas Moreau [[https://iclr-blogposts.github.io/2024/blog/bench-hvp/][How to compute Hessian-vector products?]] was accepted to ICLR 2024 as /spotlight/.

* [2024-03-01 Fri]
*Visiting Flatiron Institute NYC*. Visiting [[https://alberto.bietti.me][A. Bietti]] at [[https://www.simonsfoundation.org/flatiron/center-for-computational-mathematics/][CCM, Flatiron Institute, NYC]]. I presented our work on iterative automatic differentiation.

* [2024-01-24 Wed]
*Talk at PEPR PDE-AI kickoff*. Talk at the kickoff meeting of the [[https://pde-ai.math.cnrs.fr/][PEPR PDE-AI]] project.

* [2024-01-20 Sat]
*Two papers accepted to AISTATS 2024*. Our papers [[https://arxiv.org/abs/2304.08061][Provable local learning rule by expert aggregation for a Hawkes network]] and [[https://arxiv.org/abs/2302.08766][A Lower Bound and a Near-Optimal Algorithm for Bilevel Empirical Risk Minimization]] were accepted to AISTATS 2024.

* [2017-10-24 Tue]
*Graph-Slope paper accepted in EJS*. Our paper with [[http://www.stat.rutgers.edu/home/PCB71/][Pierre C. Bellec]] and [[https://josephsalmon.eu/][Joseph Salmon]] coined [[https://arxiv.org/abs/1706.06977][A sharp oracle inequality for Graph-Slope]] has been accepted in Electronic Journal of Statistics.

* [2017-06-21 Wed]
*Preprint on Graph-Slope*. Together with [[http://www.stat.rutgers.edu/home/PCB71/][Pierre C. Bellec]] and [[https://josephsalmon.eu/][Joseph Salmon]], we released our preprint [[https://arxiv.org/abs/1706.06977][A sharp oracle inequality for Graph-Slope]].

* [2017-04-16 Sun]
*Model Consistency of Partly Smooth Regularizers accepted in TIT*. After two long years in review, our paper with J. Fadili and G. Peyré [[http://hal.archives-ouvertes.fr/hal-00987293][Model Consistency of Partly Smooth Regularizers]] has been accepted for publication in IEEE Transactions on Information Theory.

* [2017-03-20 Mon]
*Accelerated alternating descent methods published in JMIV*. Our paper with A. Chambolle and P. Tan, [[https://hal.archives-ouvertes.fr/hal-01346532][Accelerated Alternating Descent Methods for Dykstra-like problems]] has been accepted for publication in Journal of Mathematical Imaging and Vision. The online first version is available [[https://link.springer.com/article/10.1007/s10851-017-0724-6][here]].

* [2017-02-14 Tue]
*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 [[https://hal.archives-ouvertes.fr/hal-01467965][Maximal solutions of sparse analysis regularization]].

* [2016-12-03 Sat]
*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 [[https://arxiv.org/abs/1606.05158][CLEAR: Covariant LEAst-square Re-fitting with applications to image restoration]].

* [2016-07-22 Fri]
*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 [[https://hal.archives-ouvertes.fr/hal-01346532][Accelerated Alternating Descent Methods for Dykstra-like problems]].

* [2016-06-16 Thu]
*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 [[https://arxiv.org/abs/1606.05158][CLEAR: Covariant LEAst-square Re-fitting with applications to image restoration]].

* [2016-04-01 Fri]
*Paper accepted*. Our paper [[http://hal.archives-ouvertes.fr/hal-00981634][The Degrees of Freedom of Partly Smooth Regularizers]] has been accepted for publication in Annals of the Institute of Statistical Mathematics (AISM).

* [2015-11-03 Tue]
*MOA Workshop 2015*. We organize at the [[http://math.u-bourgogne.fr/][IMB]] the annual workshop of the [[http://gdrmoa.math.cnrs.fr/][GdR MOA]] in December 2015. It will highlight recent advances in optimization. More information [[/events/journees-moa-2015][here]].

* [2015-10-28 Wed]
*PhD PGMO award*. I received one of the two PGMO PhD award for my thesis. This award is delivered by [[http://www.fondation-hadamard.fr/pgmo.php?url=95.142.164.215/fr/prixthese][Programme Gaspard Monge pour l'optimisation et la recherche opérationnelle]].

* [2015-10-01 Thu]
*CNRS*. My postdoctoral position is over and I am now a CNRS researcher (CR2). I joined the [[http://math.u-bourgogne.fr/][IMB]] at [[http://www.u-bourgogne.fr/][Université de Bourgogne]].

* [2015-04-02 Thu]
*PhD award*. I received a best PhD award for my thesis. This award is delivered by [[http://www.fondation.dauphine.fr/][Fondation Dauphine]].

* [2015-01-12 Mon]
*Two new papers*. Our paper [[http://hal.archives-ouvertes.fr/hal-00842603][Model Selection with Low Complexity Priors]] has been accepted for publication Information and Inference (IMAIAI). Moreover, our book chapter [[http://hal.archives-ouvertes.fr/hal-01018927][Low Complexity Regularization of Linear Inverse Problems]] will be published in /Sampling Theory, a Renaissance/ edited by G. Pfander.

* [2014-10-01 Wed]
*New Position*. I just started my postdoc with [[http://www.cmap.polytechnique.fr/~antonin/][Antonin Chambolle]] at the CMAP, Ecole Polytechnique.

* [2014-08-19 Tue]
*SUGAR*. Our paper [[http://hal.archives-ouvertes.fr/hal-00987295][Stein Unbiased GrAdient estimator of the Risk (SUGAR) for multiple parameter selection]] has been accepted for publication in [[http://www.siam.org/journals/siims.php][SIAM Journal on Imaging Sciences]].

* [2014-07-10 Thu]
*Ph. D.*. I successfully defended my PhD dissertation, see [[/publications/vaiter2014phd/][this page]] for more information.

* [2014-05-05 Mon]
*Preprints on Model Stability and Stein Estimation*. [[http://hal.archives-ouvertes.fr/hal-00987293][Model Consistency of Partly Smooth Regularizers]] and [[http://hal.archives-ouvertes.fr/hal-00987295][Stein Unbiased GrAdient estimator of the Risk (SUGAR) for multiple parameter selection]] are now available online.

* [2014-04-22 Tue]
*Preprint DOF*. Our last preprint [[http://hal.archives-ouvertes.fr/hal-00981634][The Degrees of Freedom of Partly Smooth Regularizers]] is available online.