Researcher
Head of Data Science Department
SDD
Data Science
Digital traces of all human activities are now available in all fields, data that is often massive, heterogeneous, dynamic and of variable quality (the 4 V’s of Big Data: Volume, Variety, Velocity, Veracity). Their exploitation leads to the definition of a fourth scientific paradigm: the design and validation of hypotheses, theoretical models and algorithms, guided by the data and in interaction with domain experts. The Data Science department is interested in robustly addressing the challenges of the 4Vs, in terms of scaling up in the face of data volume and velocity, and resisting diversity and quality bias. These goals define new computational issues in storage, communication, analysis and processing optimization, data query and enrichment, knowledge discovery, and model learning.
With nearly 40 researchers and teacher-researchers, the Data Science department covers a broad spectrum of fundamental and application-related topics: databases, data mining, semantic web, knowledge representation, algorithms, combinatorics, stochastic and distributed optimization, statistical learning and neural networks, communication networks, simulation. It also has extensive expertise in interdisciplinary research and dialogue with experts in the application domains (particularly in biology, medicine, human and social sciences, and experimental physics), allowing privileged access to data of interest and to the evaluation of models and algorithms.
Coordination
-
-
Researcher
Recent publications
-
Pré-publication, Document de travail
Alex Davey, Théo Rudkiewicz, Stéphane Rivaud, Stella Douka, Félix Houdouin, et al.. The Neuron Addition Problem: A Survey on Growing Neural Networks. 2026. ⟨hal-05842579⟩
-
Rapport
Théo Rudkiewicz, Manon Verbockhaven. On Reduced Rank Regression. Université Paris-Saclay; INRIA. 2026. ⟨hal-05802741⟩
-
Logiciel
Sylvain Chevallier. MDLA – Multivariate Dictionary Learning Algorithm. 2026, ⟨swh:1:dir:1ed1898dbf4feb86843700917be3f7c7ef29efe5;origin=https://hal.archives-ouvertes.fr/hal-05676449;visit=swh:1:snp:e36ffb7cbcc1c58ae7bb7ca90ec9cbf68265d80c;anchor=swh:1:rel:c40398f508f9151f853ebc16cea30169c3d8f43a;path=/⟩. ⟨hal-05676449⟩
-
Pré-publication, Document de travail
Théophile Sanchez, Pierre Jobic, Cyril Regan, Paul Verdu, Guillaume Charpiat, et al.. Attentive-SPIDNA: Attention-based neural networks for population genetics. 2026. ⟨hal-05688902⟩
-
Pré-publication, Document de travail
Dylan Sechet, Marc Evrard, Matthieu Kowalski. Adapting offline models to a streaming context for music source separation. 2026. ⟨hal-05767849⟩
-
Article dans une revue
Bruna Lopes, Gabriel Schwartz, Sylvain Chevallier, Raphael Y de Camargo, Bruno Aristimunha. Learning aligned EEG representations with subject-specific encoders. Scientific Reports, 2026, ⟨10.1038/s41598-026-69220-z⟩. ⟨hal-05758650⟩
-
Communication dans un congrès
Sébastien Velut, Stella Douka, Théo Rudkiewicz, Alex Davey, Stéphane Rivaud, et al.. Tackling brain signal inter-subject variability with adaptive neural architectures. IJCNN 2026 – 2026 International Joint Conference on Neural Network, IEEE, Jun 2026, Maastricht, Netherlands. ⟨hal-05752385⟩
-
Article dans une revue
Léo Planche, Anna Ilina, María C Ávila-Arcos, Flora Jay, Emilia Huerta-Sanchez, et al.. An archaic reference-free method to jointly infer Neanderthal and Denisovan introgressed segments in modern human genomes. Molecular Biology and Evolution, 2025, ⟨10.1093/molbev/msag235⟩. ⟨hal-05747173⟩
-
Article dans une revue
Marco Rosario Capodiferro, Léo Planche, Emily M Breslin, Linda Ongaro, María C Ávila-Arcos, et al.. Archaic ancestry inference in imputed ancient human genomes. Nature Communications, 2026, 17 (1), pp.9480. ⟨10.1038/s41467-026-76204-0⟩. ⟨hal-05747161⟩
-
Communication dans un congrès
Dylan Sechet, Marc Evrard, Matthieu Kowalski. Simulation-Based Inference for Plate Reverb System Identification. DAFX 2026 – 29th International Conference on Digital Audio Effects, Sep 2026, Cambridge, United States. ⟨hal-05742718⟩
-
Communication dans un congrès
Brahim Driss, Alex Davey, Riad Akrour. PB$^2$: Preference Space Exploration via Population-Based Methods in Preference-Based Reinforcement Learning. RLC 2026 – Third Reinforcement Learning Conference, Aug 2026, Montreal, Canada. ⟨hal-05732524⟩
-
Logiciel
Alexandre Barachant, Quentin Barthélemy, Gabriel Wagner Vom Berg, Alexandre Gramfort, Sylvain Chevallier, et al.. pyRiemann. 2026, ⟨swh:1:dir:99d04d80bb390054f73700b971236958727e9c55;origin=https://github.com/pyRiemann/pyRiemann;visit=swh:1:snp:42707203ccd68219f2c48dd52388fdaf0c91a420;anchor=swh:1:rev:854804d34bc7b40b318323520be896d97d8aa859⟩. ⟨hal-05676137⟩
-
Logiciel
Grégoire Cattan, Quentin Barthélemy, Anton Andreev, Sylvain Chevallier, Vedant Patare, et al.. pyRiemann-qiskit. 2026, ⟨swh:1:dir:8b5612aedfe0d134a3dab99d574106412915ae4d;origin=https://github.com/pyRiemann/pyRiemann-qiskit;visit=swh:1:snp:9dfc0df92cc1fa97758f76c4b7b2f7314973f773;anchor=swh:1:rev:14df49d9c2bfed5372f8f59b5b8fa7120dfd1b6f⟩. ⟨hal-05676343⟩
-
Communication dans un congrès
Bruno Aristimunha, Dung Truong, Pierre Guetschel, Seyed Yahya Shirazi, Isabelle Guyon, et al.. EEG Foundation Challenge: From Cross-Task to Cross-Subject EEG Decoding. NeurIPS 2025 – 39th Annual Conference on Neural Information Processing Systems, Dec 2025, San Diego, United States. ⟨hal-05714360⟩
-
Article dans une revue
Alice Lacan, Romain André, Michèle Sebag, Blaise Hanczar. In silico generation of gene expression profiles using diffusion models. BMC Bioinformatics, 2026, 27 (1), pp.160. ⟨10.1186/s12859-026-06470-8⟩. ⟨hal-05714728⟩
-
Pré-publication, Document de travail
Bruno Aristimunha, Ce Ju, Antoine Collas, Florent Bouchard, Ammar Mian, et al.. SPD Learn: A Geometric Deep Learning Python Library for Neural Decoding Through Trivialization. 2026. ⟨hal-05714371⟩
-
Communication dans un congrès
Alex Davey, Alena Shilova, Brahim Driss, Riad Akrour. StaQ: a Finite Memory Approach to Discrete Action Policy Mirror Descent. RLC 2026 – Third Reinforcement Learning Conference, Aug 2026, Montreal, Canada. ⟨hal-05710283⟩
-
Communication dans un congrès
Benedictus Kent Rachmat, Thomas Gerald, Zheng Zhang, Cyril Grouin. QA Analysis in Medical and Legal Domains: A Survey of Data Augmentation in Low-Resource Settings. ACL 2025 – 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), ACL, Jul 2025, Vienna, Austria. pp.1132-1144, ⟨10.18653/v1/2025.acl-srw.89⟩. ⟨hal-05683004⟩
-
Pré-publication, Document de travail
Marco Crialesi-Esposito, Alienor Riviere, Sergio Chibbaro. Sub-Kolmogorov Intermittency and Multifractal Dissipation in Multiphase Turbulence. 2026. ⟨hal-05679015⟩
-
Pré-publication, Document de travail
Flavio Tuteri, Sergio Chibbaro, Alexandros Alexakis. Intermittency in Shell Models of Turbulent Cascades: from Single-Branch to Multi-Branch. 2026. ⟨hal-05679006⟩
-
Logiciel
Bruno Aristimunha, Igor Carrara, Pierre Guetschel, Sara Sedlar, Pedro Rodrigues, et al.. Mother of all BCI Benchmarks. 2026, ⟨swh:1:dir:6d89a182d4e69572a73784c6616ef1cee5493d77⟩. ⟨hal-05675918⟩
-
Thèse
Bruno Aristimunha Pinto. Learning Representations of Electroencephalogram using Deep Learning. Machine Learning [cs.LG]. Université Paris-Saclay; Universidade Federal do ABC, 2026. English. ⟨NNT : 2026UPASG016⟩. ⟨tel-05668261⟩
-
Thèse
Eva Boguslawski. Politiques d’apprentissage par renforcement pour l’exploitation de réseaux électriques avec actions continues dans des architectures centralisées et décentralisées. Intelligence artificielle [cs.AIArtificial Intelligence]. Université Paris-Saclay, 2026. Français. ⟨NNT : 2026UPASG028⟩. ⟨tel-05657134⟩
-
Thèse
Cyriaque Rousselot. Deep Learning for Spatio-Temporal Pesticide Exposure Modeling : Extrapolation, Interpretability, and Constraints. Computer Science [cs]. Université Paris-Saclay, 2026. English. ⟨NNT : 2026UPASG023⟩. ⟨tel-05653218⟩
-
Poster de conférence
Louis Hernandez, Matthieu Boussard, Alessandro Leite. Harnessing Open-Source Large Language Models for Causal Discovery. EuroCIM 2025 – European causal inference meeting, Apr 2025, Ghent, Belgium. ⟨hal-05605983⟩
-
Communication dans un congrès
Hugo Thimonier, José Lucas de Melo Costa, Fabrice Popineau, Arpad Rimmel, Bich-Liên Doan. T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular Data. ICLR 2025 – International Conference on Learning Representations, Apr 2025, Sinagpore, Singapore. ⟨10.48550/arXiv.2410.05016⟩. ⟨hal-05624276⟩
-
Article dans une revue
Isabelle Hoxha, Sylvain Chevallier, Arnaud Delorme, Michel-Ange Amorim. Modality-specific predictive templates in pre-stimulus EEG activity. Neuropsychologia, 2026, 229, pp.109486. ⟨10.1016/j.neuropsychologia.2026.109486⟩. ⟨hal-05636990⟩
-
Article dans une revue, Article dans une revue
Jean-Baptiste Malagnoux, Matthieu Kowalski. Connecting the Dots Between CDL and NMF: A Shared Framework for Time-Frequency Decomposition. IEEE Transactions on Signal Processing, 2026, 74, pp.2448-2460. ⟨10.1109/TSP.2026.3698440⟩. ⟨hal-05635856⟩
-
Communication dans un congrès
Lucas Heck dos Santos, João Guilherme Prado Barbon, Sylvain Chevallier, Denis G Fantinato. Non-Linear Activation Functions for Deep Riemannian Neural Networks. ESANN 2026 – 34th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Apr 2026, Bruges, Belgium. pp.535-540, ⟨10.14428/esann/2026.ES2026-312⟩. ⟨hal-05616889⟩
-
Article dans une revue
Li-Qing Jiang, Amanda Fay, Jens Daniel Müller, Luke Gregor, Alizée Roobaert, et al.. Synthesis of data products for ocean carbonate chemistry. Earth System Science Data, 2026, 18 (2), pp.1405 – 1462. ⟨10.5194/essd-18-1405-2026⟩. ⟨hal-05607765⟩
-
Pré-publication, Document de travail
Alper Kalle, Théo Rudkiewicz, Mohamed-Oumar Ouerfelli, Mohamed Tamaazousti. Distribution-aware tensor decomposition for compression of convolutional neural networks. 2026. ⟨cea-05569665⟩
-
Poster de conférence
Arnaud Quelin, Flora Jay, Frederic Austerlitz. Inferring demographic history of diverging populations from human genomic data. SMBE, Jul 2023, Ferrara, Italy. ⟨hal-05570993⟩
-
Communication dans un congrès
Arnaud Quelin, Frederic Austerlitz, Flora Jay. Using supervised machine learning methods to infer demographic history from genomic data. Machine Learning for Evolutionary Genomics Data, May 2024, Heraklion, Greece. ⟨hal-05570974⟩
-
Poster de conférence
Arnaud Quelin, Jazeps Medina Tretmanis, Emilia Huerta-Sanchez, Frederic Austerlitz, Flora Jay. Assessing the contribution of ancient genomic data to the inference of historical demographic parameters. JOBIM 2025 – Journées Ouvertes en Biologie, Informatique et Mathématiques, Jul 2025, Bordeaux, France. ⟨hal-05570966⟩
-
Communication dans un congrès
Jean Cury, Théophile Sanchez, Erik Madison Bray, Jazeps Medina-Tretmanis, María Ávila-Arcos, et al.. Inferring effective population sizes of bacterial populations while accounting for unknown recombination and selection: a deep learning approach. ECML PKDD 2022 – Machine Learning for Microbial Genomics workshop, Sep 2022, Grenoble, France. ⟨hal-05554282⟩
-
Article dans une revue
Sébastien Velut, Jordy Thielen, Sylvain Chevallier, Marie-Constance Corsi, Frédéric Dehais. Neurophysiological screening of individual variability for robust decoding in c-VEP-based BCI. Imaging Neuroscience, 2026, 4, pp.IMAG.a.1172. ⟨10.1162/IMAG.a.1172⟩. ⟨hal-05546237⟩
-
Poster de conférence
Cyriaque Rousselot, Olivier Allais, Philippe Caillou, Julia Mink, Florian Yger. Pesticide Aerial Concentration : Estimations Toward Population Health Impact Assessment. E4H – Engineering for Health Annual Forum 2025, Nov 2025, Palaiseau (Ecole Polytechnique), France. ⟨hal-05447129⟩
-
Communication dans un congrès
Enrico Marchesini, Eva Boguslawski, Alessandro Leite, Christopher Amato, Matthieu Dussartre, et al.. MARL2GRID-TR: A multi-agent RL benchmark in power grid operations. ICLR 2026 – 14th International Conference on Learning Representations, Apr 2026, Rio de Janeiro, Brazil. ⟨hal-05532479⟩
-
Pré-publication, Document de travail
Pierre Wolinski, Guillaume Charpiat, Yann Ollivier. Asymmetrical Scaling Layers for Stable Network Pruning. 2020. ⟨hal-05524815⟩
-
Article dans une revue, Article dans une revue
Mathurin Videau, Alessandro Leite, Marc Schoenauer, Olivier Teytaud. Evolutionary Pre-Prompt Optimization for Mathematical Reasoning. ACM Transactions on Evolutionary Learning and Optimization, 2026, ⟨10.1145/3797028⟩. ⟨hal-05492969⟩
-
Communication dans un congrès
Ludovic Arnold, Sébastien Rebecchi, Sylvain Chevallier, Hélène Paugam-Moisy. An Introduction to Deep Learning. European Symposium on Artificial Neural Networks (ESANN), Apr 2011, Bruges, Belgium. ⟨hal-01352061⟩
-
Pré-publication, Document de travail
Armand Lacombe, Michèle Sébag. Asymmetrical Latent Representation for Individual Treatment Effect Modeling. 2026. ⟨hal-05490226⟩
-
Thèse
Nilo Schwencke. Natural gradients and kernel methods for Physics Informed Neural Networks (PINNs). Machine Learning [cs.LG]. Université Paris-Saclay, 2025. English. ⟨NNT : 2025UPASG087⟩. ⟨tel-05474926v2⟩
-
Thèse
Jean-Baptiste Malagnoux. Apprentissage de dictionnaires convolutifs et factorisation non négative de matrices pour la séparation de sources et les problèmes inverses. Mathématiques [math]. Université Paris-Saclay, 2025. Français. ⟨NNT : 2025UPASG096⟩. ⟨tel-05472451v2⟩
-
Thèse
Alice Lacan. Transcriptomics data generation with deep generative models. Artificial Intelligence [cs.AIArtificial Intelligence]. Université Paris-Saclay, 2025. English. ⟨NNT : 2025UPASG010⟩. ⟨tel-04996930⟩
-
Thèse
Antoine Szatkownik. Modélisation générative dans un espace latent et évaluation de données synthétiques en génomique des populations. Informatique [cs]. Université Paris-Saclay, 2025. Français. ⟨NNT : 2025UPASG109⟩. ⟨tel-05475569v2⟩
-
Communication dans un congrès
Burak Yelmen, Merve Nur Güler, Tõnu Kollo, Märt Möls, Guillaume Charpiat, et al.. Bias in genome-wide association test statistics due to omitted interactions. RECOMB 2026 – 30th Annual International Conference on Research in Computational Molecular Biology, May 2026, Thessaloniki, Greece. ⟨10.1101/2025.11.21.689603⟩. ⟨hal-05474710⟩
-
Article dans une revue
Michael Tangermann, Sylvain Chevallier, Matthias Dold, Pierre Guetschel, Reinmar Kobler, et al.. Learning from small datasets — review of workshop 6 of the 10th International BCI Meeting 2023. Journal of Neural Engineering, 2025, 22 (3), pp.033001. ⟨10.1088/1741-2552/addf80⟩. ⟨hal-05462858⟩
-
Article dans une revue, Article dans une revue
Anaclara Alvez-Canepa, Cyril Furtlehner, François Landes. Learning and extrapolating scale-invariant processes. Physical Activity Review, 2026, 114 (2), pp.025301. ⟨10.1103/n1nt-spjp⟩. ⟨hal-05470825v2⟩
-
Communication dans un congrès
Giovanni Catania, Aurélien Decelle, Cyril Furtlehner, Beatriz Seoane. A theoretical framework for overfitting in energy-based modeling. ICML 2025 – 42nd International Conference on Machine Learning, Jul 2025, Vancouver, Canada. pp.6891-6919. ⟨hal-05466288⟩
-
Pré-publication, Document de travail
Sergio Chibbaro, Cyril Furtlehner, Théo Marchetta, Andrei-Tiberiu Pantea, Davide Rossetti. Building causation links in stochastic nonlinear systems from data. 2025. ⟨hal-05466316⟩
-
Thèse
Audrey Poinsot. Structural Causal Models for Synthetic Data Generation. Other [cs.OH]. Université Paris-Saclay, 2025. English. ⟨NNT : 2025UPASG097⟩. ⟨tel-05461449⟩
-
Pré-publication, Document de travail
Panayiotis Panayiotou, Audrey Poinsot, Alessandro Leite, Nicolas Chesneau, Marc Schoenauer, et al.. CausalProfiler: Generating Synthetic Benchmarks for Rigorous and Transparent Evaluation of Causal Machine Learning. 2026. ⟨hal-05455135⟩
-
Communication dans un congrès
Mathurin Videau, Badr Youbi Idrissi, Alessandro Leite, Marc Schoenauer, Olivier Teytaud, et al.. From Bytes to Ideas: Language Modeling with Autoregressive U-Nets. NeurIPS 2025 – 39th Annual Conference on Neural Information Processing Systems, Dec 2025, San Diego, United States. ⟨10.52202/085713-3144⟩. ⟨hal-05444961⟩
-
Article dans une revue
Fernando A Villanea, David Peede, Eli J Kaufman, Valeria Añorve-Garibay, Elizabeth T Chevy, et al.. The MUC19 gene: An evolutionary history of recurrent introgression and natural selection. Science, 2025, 389 (6762), pp.eadl0882. ⟨10.1126/science.adl0882⟩. ⟨hal-05410793⟩
-
Pré-publication, Document de travail
Romain Mussard, Aurélien Gauffre, Ihsan Ullah, Thanh Gia Hieu Khuong, Massih-Reza Amini, et al.. Stylized Meta-Album: Group-bias injection with style transfer to study robustness against distribution shifts. 2025. ⟨hal-05371736⟩
-
Pré-publication, Document de travail
Miriam Bravo-Lopez, Eduardo Arrieta-Donato, Viridiana Villa-Islas, Åshild Joanne Vågene, Ana Villaseñor-Altamirano, et al.. Ancient genomic insights into Salmonella enterica Paratyphi C from Central Mexico. 2025. ⟨hal-05407381⟩
-
Article dans une revue
Daniele Noto, Alexandre Allauzen, Sergio Chibbaro. An efficient training method to learn a model of turbulence. The European Physical Journal Plus, 2024, 139 (3), pp.298. ⟨10.1140/epjp/s13360-024-05056-8⟩. ⟨hal-05356011⟩
-
Communication dans un congrès
Nicolas Atienza, Johanne Cohen, Christophe Labreuche, Michèle Sébag. Provably safeguarding a classifier from OOD and adversarial samples. ICLR 2025 – 13th International Conference on Learning Representations, Apr 2025, Singapore, Singapore. pp.56800-56820. ⟨hal-05361525v2⟩
-
Communication dans un congrès
Eliott Pradeleix, Rémy Hosseinkhan-Boucher, Alena Shilova, Onofrio Semeraro, Lionel Mathelin. Learning Meets Differential Equations: From Theory to Applications Learning non-Markovian Dynamical Systems with Signature-based Encoders. ML-DE 2025 – 2nd Workshop on “Machine Learning Meets Differential Equations: From Theory to Applications”, Oct 2025, Bologna, Italy. pp.1-25. ⟨hal-05379481⟩
-
Article dans une revue, Article dans une revue
Fanny Pouyet, Ferdinand Petit, Jérémy Guez, Léo Planche, Evelyne Heyer, et al.. Comparing ARG inference methods under transmission of reproductive success: Tree imbalance matters. Genome Biology and Evolution, 2026, 18 (9), pp.evag215. ⟨10.1093/gbe/evag215⟩. ⟨hal-05347078v2⟩
-
Pré-publication, Document de travail
Elsa Denakpo, Nicolas Dias, Johann Pitout, Thierry Naas, Dylan Pillai, et al.. Imputing missing minimum inhibitory concentration (MIC) values for Pseudomonas aeruginosa strains with a Denoising AutoEncoder. 2025. ⟨hal-05361361⟩
-
Article dans une revue
Qiaomei Fu, Heng Li, Priya Moorjani, Flora Jay, Sergey Slepchenko, et al.. Genome sequence of a 45,000-year-old modern human from western Siberia. Nature, 2014, 514 (7523), pp.445-449. ⟨10.1038/nature13810⟩. ⟨hal-05361150⟩
-
Article dans une revue
Arnaud Quelin, Frédéric Austerlitz, Flora Jay. Assessing simulation-based supervised machine learning for demographic parameter inference from genomic data. Heredity, 2025, 134 (7), pp.417-426. ⟨10.1038/s41437-025-00773-x⟩. ⟨hal-05335745⟩
-
Communication dans un congrès
Francesco Pezzicoli, Valentina Ros, François P. Landes, Marco Baity-Jesi. Class Imbalance in Anomaly Detection: Learning from an Exactly Solvable Model. AISTATS 2025 – 28th International Conference on Artificial Intelligence and Statistics, May 2025, Phuket, Thailand. ⟨10.48550/arXiv.2501.11638⟩. ⟨hal-05332794⟩
-
Communication dans un congrès, Communication dans un congrès
Alena Shilova, Alex Davey, Brahim Driss, Riad Akrour. StaQ it! Growing neural networks for Policy Mirror Descent. EWRL — Eighteenth European Workshop on Reinforcement Learning, Sep 2025, Tubingen, Germany. ⟨10.48550/arXiv.2506.13862⟩. ⟨hal-05118839⟩
-
Communication dans un congrès
Solal Nathan, Guillaume Bied, Elia Pérennès, Philippe Caillou, Bruno Crépon, et al.. JoLA: Job Landscape Aware Job Recommendation. RecSys in HR 2025 – The 5th Workshop on Recommender Systems for Human Resources, in conjunction with the 19th ACM Conference on Recommender Systems, Toine Bogers; Mesut Kaya; Chris Johnson; Jens-Joris Decorte; Guillaume Bied, Sep 2025, Prague, Czech Republic. ⟨hal-05341058⟩
-
Article dans une revue
Mathurin Videau, Alessandro Leite, Marc Schoenauer, Olivier Teytaud. Mixture of Experts for Image Classification: What’s the Sweet Spot?. Transactions on Machine Learning Research , 2025. ⟨hal-05329451⟩
-
Pré-publication, Document de travail
Antoine Szatkownik, Aurélien Decelle, Beatriz Seoane, Nicolas Béreux, Léo Planche, et al.. PRIVET: PRoximIty leakage detection Via Extreme value Theory. 2026. ⟨hal-05326013v2⟩
-
Communication dans un congrès
Thibault de Surrel, Florian Yger, Fabien Lotte, Sylvain Chevallier. A probabilistic view on Riemannian machine learning models for SPD matrices. GSI 2025 – 7th International Conference on Geometric Science of Information, Oct 2025, Saint Malo, France. pp.142-151, ⟨10.1007/978-3-032-03924-8_15⟩. ⟨hal-05343695⟩
-
Article dans une revue
Aurore Semeux-Bernier, Francesca Bonini, Samuel Medina Villalon, Maria Fratello, Matthieu Kowalski, et al.. Classification of magnetoencephalographic independent components in epilepsy by machine learning. Clinical Neurophysiology, 2025, 180, pp.2111377. ⟨10.1016/j.clinph.2025.2111377⟩. ⟨hal-05324467⟩
-
Pré-publication, Document de travail
Nilo Schwencke, Cyriaque Rousselot, Alena Shilova, Cyril Furtlehner. AMStraMGRAM: Adaptive Multi-cutoff Strategy Modification for ANaGRAM. 2025. ⟨hal-05302122⟩
-
Communication dans un congrès
Jean-Baptiste Malagnoux, Matthieu Kowalski. Convolutive Sparse Decomposition in Inverse Problems: A Sensor Space Approach. SampTA 2025 – International Conference on Sampling Theory and Applications, Jul 2025, Vienne, Austria. ⟨10.1109/SampTA64769.2025.11133530⟩. ⟨hal-05288460⟩
-
Communication dans un congrès
Vianney Taquet, Vincent Blot, Thomas Morzadec, Louis Lacombe, Nicolas J-B. Brunel. MAPIE: an open-source library for distribution-free uncertainty quantification. ICML 2022 – Workshop Distribution Free and Uncertainty Quantification ICML, Jul 2022, Baltimore / Hybrid, United States. ⟨hal-05232300⟩
-
Poster de conférence
Maël Lefeuvre, Michael D. Martin, Flora Jay, Marie-Claude Marsolier, Alexis Corrochano, et al.. GRUPS-rs: a high-performance ancient DNA genetic relatedness estimation software based on pedigree simulations. Bulletins et mémoires de la Société d’Anthropologie de Paris 35(S), Jan 2023, Paris, France. 35 (S), pp.30, 2023, ⟨10.4000/bmsap.11299⟩. ⟨hal-05242408⟩
-
Poster de conférence
Maël Lefeuvre, Michael D. Martin, Flora Jay, Marie-Claude Marsolier, Alexis Corrochano, et al.. GRUPS-rs, a high-performance ancient DNA genetic relatedness estimation software relying on pedigree simulations. JOBIM 2023 – Journées Ouvertes en Biologie, Informatique et Mathématiques, Jun 2023, Multisite, France. ⟨hal-05242467⟩
-
Communication dans un congrès
Nilo Schwencke, Cyriaque Rousselot, Alena Shilova, Cyril Furtlehner. AMSTRAMGRAM : Adaptive Multi-cutoff Strategy Modification for ANaGRAM. ENUMATH 2025 – MS31 – Geometric Optimization Methods for Scientific Machine Learning, Marius Zeinhofer; Johannes Müller, Sep 2025, Heidelberg, Germany. ⟨hal-05245453⟩
-
Pré-publication, Document de travail
Alexander Goldberg, Ihsan Ullah, Thanh Gia Hieu Khuong, Benedictus Kent Rachmat, Zhen Xu, et al.. Usefulness of LLMs as an Author Checklist Assistant for Scientific Papers: NeurIPS’24 Experiment. 2025. ⟨hal-05230379⟩
-
Communication dans un congrès, Communication dans un congrès
Jad Yehya, Mansour Benbakoura, Cédric Allain, Benoît Malezieux, Matthieu Kowalski, et al.. RoseCDL: Robust and scalable convolutional dictionary learning for rare-event detection. AISTATS 2026 – 29th International Conference on Artificial Intelligence and Statistics, Society for Artificial Intelligence and Statistics, May 2026, Tanger, Morocco. ⟨10.48550/arXiv.2509.07523⟩. ⟨hal-05250429⟩
-
Communication dans un congrès
Johanne Cohen, Emmanuel Goutierre, Hayg Guler, Fatios Kapotos, Sida-Bastien Li, et al.. Modelling Dynamical Systems: Learning ODEs with No Internal ODE Resolution. 18th International Conference, RP 2024, Sep 2025, Vienne, Austria. pp.221-237, ⟨10.1007/978-3-031-72621-7_15⟩. ⟨hal-05240753⟩
-
Chapitre d'ouvrage
François Cabestaing, Sylvain Chevallier. From signals to decisions in noninvasive neural technologies. Davide Valeriani; Theresa M. Vaughan. Neural Interfaces, Academic Press; Elsevier, pp.77-90, 2025, 978-0-443-24824-5. ⟨10.1016/C2023-0-51142-5⟩. ⟨hal-05266468⟩
-
Thèse
Manon Verbockhaven. Spotting expressivity bottlenecks in neural networks and fixing them by optimal architecture growth. Neural and Evolutionary Computing [cs.NE]. Université Paris-Saclay, 2025. English. ⟨NNT : 2025UPASG022⟩. ⟨tel-05232707⟩
-
Pré-publication, Document de travail
Alice Lacan, Romain André, Michèle Sébag, Blaise Hanczar. In Silico Generation of Gene Expression profiles using Diffusion Models. 2024. ⟨hal-05195584⟩
-
Article dans une revue, Article dans une revue
Thi-Tuyet-Trang Chau, Anna E. Dudek, Hernando Ombao, Sylvain Chevallier. Impact of Surface Ocean CO2 Atlas (SOCAT) observing network extensions on the quantification of global air-sea CO2 fluxes. Science of the Total Environment, In press, 999, pp.180265. ⟨10.1016/j.scitotenv.2025.180265⟩. ⟨hal-05209651⟩
-
Article dans une revue
Edgar Jaber, Vincent Blot, Nicolas Brunel, Vincent Chabridon, Emmauel Remy, et al.. Conformal Approach to Gaussian Process Surrogate Evaluation with Coverage Guarantees. Journal of Machine Learning for Modeling and Computing, 2025, 6 (3), pp.37-68. ⟨10.1615/JMachLearnModelComput.2025054687⟩. ⟨hal-05161190⟩
-
Communication dans un congrès
Thibault de Surrel, Fabien Lotte, Sylvain Chevallier, Florian Yger. Wrapped Gaussian on the manifold of Symmetric Positive Definite Matrices. ICML 2025 – 42nd International Conference on Machine Learning, Jul 2025, Vancouver, Canada. ⟨hal-05158268⟩
-
Thèse
Jiahui Hu. Granular Insights into Financial Discourse : Fine-Grained Opinion Analysis of Expert Texts. Document and Text Processing. Université Paris-Saclay, 2023. English. ⟨NNT : 2023UPASG110⟩. ⟨tel-05153905⟩
-
Thèse
Nicolas Atienza. Towards Reliable ML : Leveraging Multi-Modal Representations, Information Bottleneck and Extreme Value Theory. Machine Learning [stat.ML]. Université Paris-Saclay, 2025. English. ⟨NNT : 2025UPASG025⟩. ⟨tel-05140441⟩
-
Communication dans un congrès
Florent Michel, Benoît Malézieux, Matthieu Kowalski, Thomas Moreau. L’entropie comme mesure de difficulté des problèmes inverses. GRETSI’23 – XXIXème Colloque Francophone de Traitement du Signal et des Images, Aug 2023, Grenoble, France. pp.1013-1016. ⟨hal-05132642⟩
-
Article dans une revue, Article dans une revue
Marion Ullmo, Nabila Aghnim, Aurélien Decelle, Miguel Aragon-Calvo. Predicting large scale cosmological structure evolution with GAN-based autoencoders. Astronomy & Astrophysics – A&A, 2026, 706, pp.A124. ⟨10.1051/0004-6361/202449845⟩. ⟨hal-04525380⟩
-
Communication dans un congrès
Dylan Sechet, Matthieu Kowalski, Samy Mokhtari, Bruno Torrésani. Revisiting CHAMPAGNE: Sparse Bayesian Learning as Reweighted Sparse Coding. SampTA 2025 – International Conference on Sampling Theory and Applications, Jul 2025, Vienna, Austria. ⟨10.1109/SampTA64769.2025.11133512⟩. ⟨hal-05130740⟩
-
Communication dans un congrès
Guillaume Attuel, Matthieu Kowalski. Disentangling Myth from Reality: A Plea for exploring New Avenues. QIP25 – Quantum Information and Probability: from Foundations to Engineering, Andrei Khrennikov, Jun 2025, Vaxjö, Sweden. ⟨hal-05114054v2⟩
-
Article dans une revue
Gianfranco Durin, Vincenzo Maria Schimmenti, Marco Baiesi, Arianna Casiraghi, Alessandro Magni, et al.. Earthquake-like dynamics in ultrathin magnetic film. Physical Review B, 2024, 110, pp.L020405. ⟨10.1103/PhysRevB.110.L020405⟩. ⟨hal-04352576⟩
-
Poster de conférence
Romain Lloria, Florent Bouchard, Sylvain Chevallier, Frédéric Pascal. Blind separation with angular criteria. Journée du labo L2S, Jun 2023, Saint-Rémy-lès-Chevreuse, France. ⟨hal-05068005⟩
-
Communication dans un congrès, Communication dans un congrès
Audrey Poinsot, Panayiotis Panayiotou, Alessandro Leite, Nicolas Chesneau, Özgür Şimşek, et al.. Position: Causal Machine Learning Requires Rigorous Synthetic Experiments for Broader Adoption. ICML 2025 – 42nd International Conference on Machine Learning, Jul 2025, Vancouver, Canada. ⟨hal-05066031v2⟩
-
Pré-publication, Document de travail
Guillaume Attuel, Matthieu Kowalski. Disentangling myth from reality: Nonlocality was not proven.. 2025. ⟨hal-04970178v8⟩
-
Poster de conférence
Cyriaque Rousselot, Olivier Allais, Philippe Caillou, Julia Mink, Florian Yger. Assessing the Impact of Pesticide Exposure on Population Health Using Large-Scale Data Integration and Modelling. E4H Annual Forum 2024 – Engineering for Health Annual Forum, Nov 2024, Palaiseau (Ecole Polytechnique), France. ⟨hal-04991195⟩
-
Communication dans un congrès, Communication dans un congrès
Stéphane Rivaud, Louis Fournier, Thomas Pumir, Eugene Belilovsky, Michael Eickenberg, et al.. PETRA: Parallel End-to-end Training with Reversible Architectures. ICLR 2025 – 13th International Conference on Learning Representations, Apr 2025, Singapour, Singapore. ⟨hal-04594647v2⟩
-
Communication dans un congrès
Cyriaque Rousselot, Olivier Allais, Philippe Caillou, Julia Mink, Florian Yger. Assessing Impact of Pesticide Exposure on Child Health using Large-Scale Data Integration and Modelling. Workshop 2024 – Qualité de l’Air, Agriculture et Santé Humaine, Nov 2024, Saint-Rémy-lès-Chevreuses, France. ⟨hal-04991175⟩
-
Thèse
Maria Sayu Yamamoto. Addressing the Large Variability of EEG Data with Riemannian Geometry : Toward Designing Reliable Brain-Computer Interfaces. Machine Learning [cs.LG]. Université Paris-Saclay, 2024. English. ⟨NNT : 2024UPASG098⟩. ⟨tel-04967163⟩