Gaël Varoquaux
Présentation
Publications
Publications
|
|
On the calibration of survival models with competing risksAISTATS 2026 - 29th International Conference on Artificial Intelligence and Statistics, May 2026, Tanger, Morocco |
|
|
Epistemic Uncertainty Quantification to Improve Decisions From Black-Box ModelsFourteenth International Conference on Learning Representations, Apr 2026, Rio de Janeiro, Brazil |
|
|
TabICL: A Tabular Foundation Model for In-Context Learning on Large DataICML 2025 - 42nd International Conference on Machine Learning, Jul 2025, Vancouver, Canada |
|
|
Scalable Feature Learning on Huge Knowledge Graphs for Downstream Machine LearningNeurIPS 2025 - 39th Annual Conference on Neural Information Processing Systems, Dec 2025, San Diego (California), United States |
|
|
Hype, Sustainability, and the Price of the Bigger-is-Better Paradigm in AIFAccT 2025 - ACM Conference on Fairness, Accountability, and Transparency, Jun 2025, Athens, Greece |
Narrative review on the clinical evaluation of AI-based digital medical devices from a methodological perspectivePEPR-SanteNum 2025 - Journées Annuelles du PEPR Santé Numérique, PEPR Santé Numérique, Oct 2025, Lille, France |
|
|
|
Decision from Suboptimal Classifiers: Excess Risk Pre-and Post-CalibrationAISTATS 2025 - the 28th International Conference on Artifi- cial Intelligence and Statistics, May 2025, Mai Khao, Thailand |
|
|
Survival Models: Proper Scoring Rule and Stochastic Optimization with Competing RisksAISTATS 2025 - 28th International Conference on Artificial Intelligence and Statistics, May 2025, Phuket, Thailand |
|
|
Imputation for prediction: beware of diminishing returnsICLR 2025 - International Conference on Learning Representations, Apr 2025, Singapore, Singapore |
|
|
Some hidden traps of confidence intervals in medical image segmentation: coverage issuesBRIDGE 2025 - MICCAI Workshop Bridging Regulatory Science and Medical Imaging Evaluation, Sep 2025, Deajeon, South Korea |
|
|
Knowledge-Rich Embeddings for Tabular LearningAITD 2025 - Workshop on AI for Tabular Data, Dec 2025, Copenhagen, Denmark |
Innovative clinical trial approach for evaluating digital medical devices under European HTA fast-Track frameworksISCB 2025 - 46th Annual Conference of the International Society for Clinical Biostatistics, Aug 2025, Basel, Switzerland |
|
|
|
Operational challenges of building a million-patient cohort from EHRs: The COhort of DIabetic patients (CODIA) on the AP-HP EDSjournée de l'Atelier TIDS (Traitement Informatique des Données de Santé) du GdR MaDICS, Oct 2024, Paris (PariSanté Campus), France |
|
|
Confidence intervals uncovered: Are we ready for real-world medical imaging AI?MICCAI 2024 - 27th International Conference on Medical Image Computing and Computer-Assisted Intervention, Oct 2024, Marrakech, Morocco. pp.124-132, ⟨10.1007/978-3-031-72117-5_12⟩ |
|
|
CARTE: Pretraining and Transfer for Tabular LearningForty-first International Conference on Machine Learning, ICML 2024, Jul 2024, Vienna, Austria |
|
|
Learning High-Quality and General-Purpose Phrase RepresentationsEACL 2024 - The 18th Conference of the European Chapter of the Association for Computational Linguistics, Mar 2024, La Valette, Malta |
|
|
Reconfidencing LLM Uncertainty from the Grouping Loss PerspectiveEMNLP 2024 - Conference on Empirical Methods in Natural Language Processing, Nov 2024, Miami, United States. ⟨10.48550/arXiv.2402.04957⟩ |
|
|
Beyond calibration: estimating the grouping loss of modern neural networksICLR 2023 – The Eleventh International Conference on Learning Representations, May 2023, Kigali, Rwanda |
|
|
The Locality and Symmetry of Positional EncodingsEMNLP 2023 - Conference on Empirical Methods in Natural Language Processing, Dec 2023, Singapore, Singapore |
|
|
GLADIS: A General and Large Acronym Disambiguation BenchmarkEACL 2023 - The 17th Conference of the European Chapter of the Association for Computational Linguistics, May 2023, Dubrovnik, Croatia |
|
|
Why do tree-based models still outperform deep learning on typical tabular data?36th Conference on Neural Information Processing Systems (NeurIPS 2022) Track on Datasets and Benchmarks, Nov 2022, New Orleans, United States |
|
|
Imputing out-of-vocabulary embeddings with LOVE makes language models robust with little costACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, May 2022, Dublin, Ireland |
|
|
AI as statistical methods for imperfect theoriesNeurIPS 2021 - 35th Conference on Neural Information Processing Systems. Workshop: AI for Science, Dec 2021, Virtual, France |
|
|
Accounting for variance in machine learning benchmarksMLsys 2021 - 4th Conference on Machine Learning and Systems, Apr 2021, San Francisco (virtual), United States |
|
|
A lightweight neural model for biomedical entity linkingAAAI 2021 - The Thirty-Fifth Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence, Feb 2021, Palo Alto (virtual), United States. pp.12657-12665 |
|
|
What's a good imputation to predict with missing values?NeurIPS 2021 - 35th Conference on Neural Information Processing Systems, Dec 2021, Virtual, France. ⟨10.48550/arXiv.2106.00311⟩ |
|
|
NeuMiss networks: differentiable programming for supervised learning with missing valuesNeurIPS 2020 - 34th Conference on Neural Information Processing Systems, Dec 2020, Vancouver / Virtual, Canada |
|
|
Linear predictor on linearly-generated data with missing values: non consistency and solutionsAISTATS 2020 - International Conference on Artificial Intelligence and Statistics, Aug 2020, Online, France. pp.3165-3174 |
|
|
Comparing distributions: $l1$ geometry improves kernel two-sample testingNeurIPS 2019 - 33th Conference on Neural Information Processing Systems, Dec 2019, Vancouver, Canada |
|
|
Feature Grouping as a Stochastic Regularizer for High-Dimensional Structured DataNeurIPS 2019 - 33th Annual Conference on Neural Information Processing Systems, Dec 2019, Vancouver, Canada |
|
|
Manifold-regression to predict from MEG/EEG brain signals without source modelingNeurIPS 2019 - 33th Annual Conference on Neural Information Processing Systems, Dec 2019, Vancouver, Canada |
|
|
Controlling a confound in predictive models with a test set minimizing its effectPRNI 2018 - 8th International Workshop on Pattern Recognition in Neuroimaging, Jun 2018, Singapore, Singapore. pp.1-4 |
|
|
Text to brain: predicting the spatial distribution of neuroimaging observations from text reportsMICCAI 2018 - 21st International Conference on Medical Image Computing and Computer Assisted Intervention, Sep 2018, Granada, Spain. pp.1-18 |
|
|
Population-shrinkage of covariance to estimate better brain functional connectivityMedical Image Computing and Computer Assisted Interventions, Sep 2017, Quebec city, Canada |
|
|
Towards a Faster Randomized Parcellation Based InferencePRNI 2017 - 7th International Workshop on Pattern Recognition in NeuroImaging, Jun 2017, Toronto, Canada |
Label scarcity in biomedicine: Data-rich latent factor discovery enhances phenotype predictionNeural Information Processing Systems, Machine Learning in Health Workshop, Dec 2017, Long Beach, United States |
|
|
|
Learning Neural Representations of Human Cognition across Many fMRI StudiesNeural Information Processing Systems, Dec 2017, Long Beach, United States |
|
|
Hierarchical Region-Network Sparsity for High-Dimensional Inference in Brain ImagingInternational conference on Information Processing in Medical Imaging (IPMI) 2017, Jun 2017, Boone, North Carolina, United States |
|
|
Multi-output predictions from neuroimaging: assessing reduced-rank linear modelsPRNI 2017 - The 7th International Workshop on Pattern Recognition in Neuroimaging, Jun 2017, Toronto, Canada. pp.1 - 4, ⟨10.1109/PRNI.2017.7981504⟩ |
|
|
Learning to Discover Sparse Graphical ModelsInternational Conference on Machine Learning , Aug 2017, Sydney, Australia |
The Brain Imaging Data Structure: a format for organizing and describing neuroimaging data22nd Annual Meeting of the Organization for Human Brain Mapping (OHBM 2016), Jun 2016, Geneva, Switzerland |
|
|
|
Dictionary Learning for Massive Matrix FactorizationInternational Conference on Machine Learning, Jun 2016, New York, United States. pp.1737-1746 |
|
|
Subsampled online matrix factorization with convergence guaranteesNIPS Workshop on Optimization for Machine Learning, Dec 2016, Barcelone, Spain |
|
|
Fast brain decoding with random sampling and random projectionsPRNI 2016: the 6th International Workshop on Pattern Recognition in Neuroimaging, Jun 2016, Trento, Italy |
|
|
Learning brain regions via large-scale online structured sparse dictionary-learningNeural Information Processing Systems (NIPS), Dec 2016, Barcelona, Spain |
|
|
Local Q-Linear Convergence and Finite-time Active Set Identification of ADMM on a Class of Penalized Regression ProblemsICASSP, International Conference on Acoustics, Speach, and Signal Processing, Mar 2016, http://icassp2016.org/default.asp, China |
|
|
Comparing functional connectivity based predictive models across datasetsPRNI 2016: 6th International Workshop on Pattern Recognition in Neuroimaging, Jun 2016, Trento, Italy |
|
|
Social-sparsity brain decoders: faster spatial sparsityPattern Recognition in NeuroImaging, Jun 2016, Trento, Italy |
|
|
Compressed Online Dictionary Learning for Fast Resting-State fMRI DecompositionInternational Symposium on Biomedical Imaging, IEEE, Apr 2016, Prague, Czech Republic. pp.1282-1285, ⟨10.1109/ISBI.2016.7493501⟩ |
|
|
Testing for Differences in Gaussian Graphical Models: Applications to Brain ConnectivityNeural Information Processing Systems (NIPS) 2016, Dec 2016, Barcelona, Spain |
|
|
Speeding-up model-selection in GraphNet via early-stopping and univariate feature-screeningPRNI, Jun 2015, Stanford, United States |
|
|
Improving sparse recovery on structured images with bagged clusteringInternational Workshop On Pattern Recognition In Neuroimaging (PRNI), 2015, Jun 2015, Palo alto, United States |
NeuroVault.org: new features and a proof of concept analysis21st Annual Meeting of the Organization for Human Brain Mapping (OHBM 2015), Jun 2015, Honolulu, United States |
|
|
|
Correlations of correlations are not reliable statistics: implications for multivariate pattern analysis.ICML Workshop on Statistics, Machine Learning and Neuroscience (Stamlins 2015), Bertrand Thirion, Lars Kai Hansen, Sanmi Koyejo, Jul 2015, Lille, France |
|
|
Semi-Supervised Factored Logistic Regression for High-Dimensional Neuroimaging DataNIPS'15: 28th International Conference on Neural Information Processing Systems, Dec 2015, Montreal, Canada |
|
|
FAASTA: A fast solver for total-variation regularization of ill-conditioned problems with application to brain imagingColloque GRETSI, P. Gonçalves, P. Abry, Sep 2015, Lyon, France |
|
|
Total Variation meets Sparsity: statistical learning with segmenting penaltiesMedical Image Computing and Computer Aided Intervention (MICCAI), Oct 2015, München, Germany |
|
|
Fast clustering for scalable statistical analysis on structured imagesICML Workshop on Statistics, Machine Learning and Neuroscience (Stamlins 2015), Bertrand Thirion, Lars Kai Hansen, Sanmi Koyejo, Jul 2015, Lille, France |
|
|
Integrating Multimodal Priors in Predictive Models for the Functional Characterization of Alzheimer's DiseaseMedical Image Computing and Computer Assisted Intervention, Oct 2015, Munich, Germany. ⟨10.1007/978-3-319-24553-9_26⟩ |
|
|
Principal Component Regression predicts functional responses across individualsMICCAI, Sep 2014, Boston, United States |
|
|
Transport on Riemannian Manifold for Functional Connectivity-based ClassificationMICCAI - 17th International Conference on Medical Image Computing and Computer Assisted Intervention, Polina Golland, Sep 2014, Boston, United States |
|
|
Deriving a multi-subject functional-connectivity atlas to inform connectome estimationMedical Image Computing and Computer-Assisted Intervention, Sep 2014, Boston, United States. pp.185-192, ⟨10.1007/978-3-319-10443-0_24⟩ |
|
|
Benchmarking solvers for TV-l1 least-squares and logistic regression in brain imagingPRNI 2014 - 4th International Workshop on Pattern Recognition in NeuroImaging, Jun 2014, Tübingen, Germany |
|
|
Cohort-level brain mapping: learning cognitive atoms to single out specialized regionsIPMI - Information Processing in Medical Imaging - 2013, William M. Wells, Sarang Joshi, Kilian M. Pohl, Jun 2013, Asilomar, United States. pp.438-449, ⟨10.1007/978-3-642-38868-2_37⟩ |
|
|
API design for machine learning software: experiences from the scikit-learn projectEuropean Conference on Machine Learning and Principles and Practices of Knowledge Discovery in Databases, Sep 2013, Prague, Czech Republic |
|
|
A Novel Sparse Group Gaussian Graphical Model for Functional Connectivity EstimationInformation Processing in Medical Imaging, Jun 2013, Asilomar, United States |
|
|
Hemodynamic estimation based on Consensus ClusteringPRNI 2013 -- 3rd International Workshop on Pattern Recognition in NeuroImaging, Jun 2013, Philadelphia, United States |
|
|
Mapping cognitive ontologies to and from the brainNIPS (Neural Information Processing Systems), Dec 2013, United States |
|
|
Robust Group-Level Inference in Neuroimaging Genetic StudiesPattern Recognition in Neuroimaging, Jun 2013, Philadelphie, United States |
|
|
Extracting brain regions from rest fMRI with Total-Variation constrained dictionary learningMICCAI - 16th International Conference on Medical Image Computing and Computer Assisted Intervention - 2013, Sep 2013, Nagoya, Japan |
|
|
Implications of Inconsistencies between fMRI and dMRI on Multimodal Connectivity EstimationMICCAI - 16th International Conference on Medical Image Computing and Computer Assisted Intervention - 2013, Kensaku Mori, Sep 2013, Nagoya, Japan |
|
|
A Comparison of Metrics and Algorithms for Fiber ClusteringPattern Recognition in NeuroImaging, Jun 2013, Philadelphia, United States |
|
|
Enhancing the Reproducibility of Group Analysis with Randomized Brain ParcellationsMICCAI - 16th International Conference on Medical Image Computing and Computer Assisted Intervention - 2013, Sep 2013, Nagoya, Japan |
|
|
Identifying predictive regions from fMRI with TV-L1 priorPattern Recognition in Neuroimaging (PRNI), Jun 2013, Philadelphia, United States |
|
|
Connectivity-informed Sparse Classifiers for fMRI Brain DecodingPattern Recognition in Neuroimaging, Christos Davatzikos, Moritz Grosse-Wentrup, Janaina Mourao-Miranda, Dimitri Van De Ville, Jul 2012, London, United Kingdom |
|
|
Improved brain pattern recovery through ranking approachesPRNI 2012 : 2nd International Workshop on Pattern Recognition in NeuroImaging, Jul 2012, London, United Kingdom |
|
|
Decoding Visual Percepts Induced by Word Reading with fMRIPattern Recognition in NeuroImaging (PRNI), 2012 International Workshop on, Jul 2012, Londres, United Kingdom. pp.13-16, ⟨10.1109/PRNI.2012.20⟩ |
|
|
A MapReduce Approach for Ridge Regression in Neuroimaging-Genetic StudiesDCICTIA-MICCAI - Data- and Compute-Intensive Clinical and Translational Imaging Applications in conjonction with the 15th International Conference on Medical Image Computing and Computer Assisted Intervention - 2012, Oct 2012, Nice, France |
|
|
Improving accuracy and power with transfer learning using a meta-analytic databaseMICCAI, Oct 2012, Nice, France. pp.1-8 |
|
|
A Comparative Study of Algorithms for Intra- and Inter-subjects fMRI DecodingMLINI - Machine Learning and Interpretation in Neuroimaging - 2011, Dec 2011, Sierra Nevada, Spain. pp.1-8, ⟨10.1007/978-3-642-34713-9_1⟩ |
|
|
Small-sample brain mapping: sparse recovery on spatially correlated designs with randomization and clusteringInternational Conference on Machine Learning, Andrew McCallum, Jun 2012, Edimbourg, United Kingdom |
|
|
A Novel Sparse Graphical Approach for Multimodal Brain Connectivity InferenceMedical Image Computing and Computer Assisted Intervention, Oct 2012, Nice, France |
|
|
A fast computational framework for genome-wide association studies with neuroimaging data20th International Conference on Computational Statistics (COMPSTAT 2012), Aug 2012, Limassol, Cyprus |
|
|
Non-parametric Density Modeling and Outlier Detection in Medical Imaging DatasetsMachine Learning in Medical Imaging - Miccai 2012 workshop, Oct 2012, Nice, France. pp.207-214 |
|
|
Statistical Learning for Resting-State fMRI: Successes and ChallengesMachine Learning and Interpretation in Neuroimaging, NIPS workshop, Dec 2011, Sierra Nevada, Spain. pp.172-177, ⟨10.1007/978-3-642-34713-9_22⟩ |
|
|
On spatial selectivity and prediction across conditions with fMRIPRNI 2012 : 2nd International Workshop on Pattern Recognition in NeuroImaging, Jul 2012, London, United Kingdom. pp.53-56 |
|
|
Learning to rank from medical imaging dataThird International Workshop on Machine Learning in Medical Imaging - MLMI 2012, INRIA, Oct 2012, Nice, France |
|
|
Detecting Outlying Subjects in High-Dimensional Neuroimaging Datasets with Regularized Minimum Covariance DeterminantMedical Image Computing and Computer Assisted Intervention, Sep 2011, Toronto, Canada. pp. 264-271, ⟨10.1007/978-3-642-23626-6_33⟩ |
|
|
Beyond brain reading: randomized sparsity and clustering to simultaneously predict and identifyNIPS 2011 MLINI Workshop, Dec 2011, Granada, Spain. pp.9-16, ⟨10.1007/978-3-642-34713-9_2⟩ |
|
|
A probabilistic framework to infer brain functional connectivity from anatomical connectionsInformation Processing in Medical Imaging, Gábor Székely, Horst Hahn, Jul 2011, Kaufbeuren, Germany. pp.296-307, ⟨10.1007/978-3-642-22092-0_25⟩ |
|
|
MULTIFRACTAL ANALYSIS OF RESTING STATE NETWORKS IN FUNCTIONAL MRIIEEE International Symposium on Biomedical Imaging, Mar 2011, Chicago, United States. paper ID 1544 |
|
|
Connectivity-informed fMRI Activation DetectionMedical Image Computing and Computed Aided Intervention, Sep 2011, Toronto, Canada. pp.285-292, ⟨10.1007/978-3-642-23629-7_35⟩ |
|
|
Multi-subject dictionary learning to segment an atlas of brain spontaneous activityInformation Processing in Medical Imaging, Gábor Székely, Horst Hahn, Jul 2011, Kaufbeuren, Germany. pp.562-573, ⟨10.1007/978-3-642-22092-0_46⟩ |
|
|
Total Variation regularization enhances regression-based brain activity prediction1st ICPR Workshop on Brain Decoding - Pattern recognition challenges in neuroimaging - 20th International Conference on Pattern Recognition, Aug 2010, Istanbul, Turkey. pp.9-12, ⟨10.1109/WBD.2010.13⟩ |
|
|
ICA-based sparse feature recovery from fMRI datasetsBiomedical Imaging, IEEE International Symposium on, Apr 2010, Rotterdam, Netherlands. pp.1177 |
|
|
Brain covariance selection: better individual functional connectivity models using population priorAdvances in Neural Information Processing Systems, John Lafferty, Dec 2010, Vancouver, Canada |
|
|
Detection of brain functional-connectivity difference in post-stroke patients using group-level covariance modelingMedical Image Computing and Computer Added Intervention, Tianzi Jiang, Sep 2010, Beijing, China. ⟨10.1007/978-3-642-15705-9_25⟩ |
|
|
Accurate Definition of Brain Regions Position Through the Functional Landmark Approach13th International Conference on Medical Image Computing and Computer Assisted Intervention, Sep 2010, Beijing, China |
|
|
CanICA: Model-based extraction of reproducible group-level ICA patterns from fMRI time seriesMedical Image Computing and Computer Aided Intervention, Sep 2009, London, United Kingdom. pp.1 |
|
|
Proceedings of the 8th Python in Science conferenceSciPy 2009: 8th Python in Science Conference, Aug 2009, Pasadena, United States. pp.1-78 |
All-optical evaporative cooling in a versatile optical-dipole trap at telecom wavelengthYAO, 2008, Florence, Italy |
|
|
|
Proceedings of the 7th Python in Science conferenceSciPy 2008: 7th Python in Science Conference, Aug 2008, Pasadena, United States. pp.1-78 |
|
|
Mayavi: Making 3D Data Visualization ReusableSciPy 2008: 7th Python in Science Conference, Aug 2008, Pasadena, United States. pp.51 |
Effects of disorder in 2DLatsis, Jan 2008, Lausanne, Switzerland |
|
|
|
I.C.E.: An Ultra-Cold Atom Source for Long-Baseline Interferometric Inertial Sensors in Reduced GravityRencontres de Moriond Gravitational Waves and Experimental Gravity, Mar 2007, La Thuile, Val d'Aoste, Italy |
|
|
Region segmentation for sparse decompositions: better brain parcellations from rest fMRISparsity Techniques in Medical Imaging, Sep 2014, Boston, United States. pp.8 |
|
|
Scipy Lecture NotesZenodo, 2015, ⟨10.5281/zenodo.31736⟩ |
|
|
Evaluating machine learning models and their diagnostic valueOlivier Colliot. Machine Learning for Brain Disorders, Springer, 2023 |
|
|
International AI Safety Report 2025 Second Key Update: Technical Safeguards and Risk ManagementMila - Quebec AI Institute; UK AI Safety Institute. 2025 |
|
|
International AI Safety ReportAI safety institute. 2025 |
|
|
International AI Safety Report 2025 First Key Update: Capabilities and Risk ImplicationsUK AI Security Institute; Mila - Quebec AI Institute. 2025 |
|
|
International Scientific Report on the Safety of Advanced AI: interim reportDepartment for Science, Innovation and Technology. 2024 |
|
|
IA : Notre Ambition Pour La FranceGouvernement Français. 2024 |
|
|
Lessons from shortcomings in machine learning for medical imagingOECD. 2023 |
|
|
Survey of machine-learning experimental methods at NeurIPS2019 and ICLR2020[Research Report] Inria Saclay Ile de France. 2020 |
|
|
Atomic sources for long-time-of-flight interferometric inertial sensorsAtomic Physics [physics.atom-ph]. Université Paris Sud - Paris XI; Institut d'Optique, 2008. English. ⟨NNT : ⟩ |