Alexandre Gramfort
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Recognitions
Alexandre Gramfort has a total of 414 co-authors. Here are the top co-authors by number of shared publications:
- Gaël Varoquaux
Soda, Inria Saclay, Palaiseau, France
21 shared publications Bertrand Thirion
Inria Parietal Team, Inria Saclay, France; Neurospin, I2BM, DSV, CEA Saclay, France
18 shared publications- Denis Alexander Engemann
Roche Pharma Research and Early Development, Neuroscience and Rare Diseases, Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd., Basel, Switzerland
15 shared publications - Bertrand Thirion
Université Paris-Saclay, Inria, CEA, Palaiseau, France
13 shared publications - Maureen Clerc
INRIA
9 shared publications - Jens Haueisen
Institute of Biomedical Engineering and Informatics, TU Ilmenau, Ilmenau, Germany
8 shared publications
Latest Publications
- Open Access
EMG-BIDS: an extension to the Brain Imaging Data Structure for electromyography
Electromyography (EMG) is fundamental to clinical assessment, rehabilitation, neuromuscular research, and human-machine interfaces. Despite decades of use, no widely adopted standard exists for organizing and sharing EMG data, limiting reusability and large-scale data aggregation. We present EMG-BIDS, an extension to the Brain Imaging Data Structure (BIDS) that standardizes the organization of EMG recordings. EMG-BIDS addresses challenges unique to EMG, including diverse electrode types (surface or intramuscular, single channel to high-density arrays), heterogeneous electrode placements across anatomical locations, montages (e.g., monopolar or bipolar sensor designs), and the critical need for transparent documentation of sensor positioning. The specification introduces hierarchical coordinate systems that link local electrode grids to anatomical landmarks, enabling precise and reproducible placement documentation. EMG-BIDS is now part of BIDS as of version 1.11.0, supported by existing tools, including MNE-BIDS and EEGLAB. We demonstrate the specification through public datasets, including high-density surface EMG recordings. EMG-BIDS provides the foundation for FAIR (Findable, Accessible, Interoperable, Reusable) EMG data sharing, enabling meta-analyses, multi-site studies, and machine learning applications that require standardized, well-documented datasets.
Open AccessEMG-BIDS: an extension to the Brain Imaging Data Structure for electromyography
Electromyography (EMG) is fundamental to clinical assessment, rehabilitation, neuromuscular research, and human-machine interfaces. Despite decades of use, no widely adopted standard exists for organizing and sharing EMG data, limiting reusability and large-scale data aggregation. We present EMG-BIDS, an extension to the Brain Imaging Data Structure (BIDS) that standardizes the organization of EMG recordings. EMG-BIDS addresses challenges unique to EMG, including diverse electrode types (surface or intramuscular, single channel to high-density arrays), heterogeneous electrode placements across anatomical locations, montages (e.g., monopolar or bipolar sensor designs), and the critical need for transparent documentation of sensor positioning. The specification introduces hierarchical coordinate systems that link local electrode grids to anatomical landmarks, enabling precise and reproducible placement documentation. EMG-BIDS is now part of BIDS as of version 1.11.0, supported by existing tools, including MNE-BIDS and EEGLAB. We demonstrate the specification through public datasets, including high-density surface EMG recordings. EMG-BIDS provides the foundation for FAIR (Findable, Accessible, Interoperable, Reusable) EMG data sharing, enabling meta-analyses, multi-site studies, and machine learning applications that require standardized, well-documented datasets.
- 1 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 73 (2) , 945-952
MVICAD 2 : Multi-View Independent Component Analysis With Delays and Dilations
Machine learning techniques in multi-view settings face significant challenges, particularly when integrating heterogeneous data, aligning feature spaces, and managing view-specific biases. These issues are prominent in neuroscience, where data from multiple subjects exposed to the same stimuli are analyzed to uncover brain activity dynamics. In magnetoencephalography (MEG), where signals are captured at the scalp level, estimating the brain's underlying sources is crucial, especially in group studies where sources are assumed to be similar for all subjects. Common methods, such as Multi-View Independent Component Analysis (MVICA), assume identical sources across subjects, but this assumption is often too restrictive due to individual variability and age-related changes. Multi-View Independent Component Analysis with Delays (MVICAD) addresses this by allowing sources to differ up to a temporal delay. However, temporal dilation effects, particularly in auditory stimuli, are common in brain dynamics, making the estimation of time delays alone insufficient. To address this, we propose Multi-View Independent Component Analysis with Delays and Dilations (MVICAD$^{2}$), which allows sources to differ across subjects in both temporal delays and dilations. We present a model with identifiable sources, derive an approximation of its likelihood in closed form, and use regularization and optimization techniques to enhance performance. Through simulations, we demonstrate that MVICAD$^{2}$ outperforms existing multi-view ICA methods. We further validate its effectiveness using the Cam-CAN dataset, and showing how delays and dilations are related to aging.
- 1 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 73 (2) , 945-952
MVICAD 2 : Multi-View Independent Component Analysis With Delays and Dilations
Machine learning techniques in multi-view settings face significant challenges, particularly when integrating heterogeneous data, aligning feature spaces, and managing view-specific biases. These issues are prominent in neuroscience, where data from multiple subjects exposed to the same stimuli are analyzed to uncover brain activity dynamics. In magnetoencephalography (MEG), where signals are captured at the scalp level, estimating the brain's underlying sources is crucial, especially in group studies where sources are assumed to be similar for all subjects. Common methods, such as Multi-View Independent Component Analysis (MVICA), assume identical sources across subjects, but this assumption is often too restrictive due to individual variability and age-related changes. Multi-View Independent Component Analysis with Delays (MVICAD) addresses this by allowing sources to differ up to a temporal delay. However, temporal dilation effects, particularly in auditory stimuli, are common in brain dynamics, making the estimation of time delays alone insufficient. To address this, we propose Multi-View Independent Component Analysis with Delays and Dilations (MVICAD$^{2}$), which allows sources to differ across subjects in both temporal delays and dilations. We present a model with identifiable sources, derive an approximation of its likelihood in closed form, and use regularization and optimization techniques to enhance performance. Through simulations, we demonstrate that MVICAD$^{2}$ outperforms existing multi-view ICA methods. We further validate its effectiveness using the Cam-CAN dataset, and showing how delays and dilations are related to aging.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- p. 1-11
How Forgiving are M/EEG Inverse Solutions to Noise Level Misspecification? An Excursion into the BSI-Zoo
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- p. 1-11
Open AccessHow Forgiving are M/EEG Inverse Solutions to Noise Level Misspecification? An Excursion into the BSI-Zoo
- Open Access
MVICAD 2 : Multi-View Independent Component Analysis with Delays and Dilations
Machine learning techniques in multi-view settings face significant challenges, particularly when integrating heterogeneous data, aligning feature spaces, and managing view-specific biases. These issues are prominent in neuroscience, where data from multiple subjects exposed to the same stimuli are analyzed to uncover brain activity dynamics. In magnetoencephalography (MEG), where signals are captured at the scalp level, estimating the brain's underlying sources is crucial, especially in group studies where sources are assumed to be similar for all subjects. Common methods, such as Multi-View Independent Component Analysis (MVICA), assume identical sources across subjects, but this assumption is often too restrictive due to individual variability and age-related changes. Multi-View Independent Component Analysis with Delays (MVICAD) addresses this by allowing sources to differ up to a temporal delay. However, temporal dilation effects, particularly in auditory stimuli, are common in brain dynamics, making the estimation of time delays alone insufficient. To address this, we propose Multi-View Independent Component Analysis with Delays and Dilations (MVICAD²), which allows sources to differ across subjects in both temporal delays and dilations. We present a model with identifiable sources, derive an approximation of its likelihood in closed form, and use regularization and optimization techniques to enhance performance. Through simulations, we demonstrate that MVICAD² outperforms existing multi-view ICA methods. We further validate its effectiveness using the Cam-CAN dataset, and showing how delays and dilations are related to aging.
Open AccessMVICAD 2 : Multi-View Independent Component Analysis with Delays and Dilations
Machine learning techniques in multi-view settings face significant challenges, particularly when integrating heterogeneous data, aligning feature spaces, and managing view-specific biases. These issues are prominent in neuroscience, where data from multiple subjects exposed to the same stimuli are analyzed to uncover brain activity dynamics. In magnetoencephalography (MEG), where signals are captured at the scalp level, estimating the brain's underlying sources is crucial, especially in group studies where sources are assumed to be similar for all subjects. Common methods, such as Multi-View Independent Component Analysis (MVICA), assume identical sources across subjects, but this assumption is often too restrictive due to individual variability and age-related changes. Multi-View Independent Component Analysis with Delays (MVICAD) addresses this by allowing sources to differ up to a temporal delay. However, temporal dilation effects, particularly in auditory stimuli, are common in brain dynamics, making the estimation of time delays alone insufficient. To address this, we propose Multi-View Independent Component Analysis with Delays and Dilations (MVICAD²), which allows sources to differ across subjects in both temporal delays and dilations. We present a model with identifiable sources, derive an approximation of its likelihood in closed form, and use regularization and optimization techniques to enhance performance. Through simulations, we demonstrate that MVICAD² outperforms existing multi-view ICA methods. We further validate its effectiveness using the Cam-CAN dataset, and showing how delays and dilations are related to aging.
- Open Access
- 2 May 2025
- Published by MIT Press in Imaging Neuroscience
- Vol. 3
Cycling on the Freeway: The perilous state of open-source neuroscience software
Most scientists need software to perform their research (Barker et al., 2020; Carver et al., 2022; Hettrick, 2014; Hettrick et al., 2014; Switters & Osimo, 2019), and neuroscientists are no exception. Whether we work with reaction times, electrophysiological signals, or magnetic resonance imaging data, we rely on software to acquire, analyze, and statistically evaluate the raw data we obtain—or to generate such data if we work with simulations. In recent years, there has been a shift toward relying on free, open-source scientific software (FOSSS) for neuroscience data analysis (Poldrack et al., 2019), in line with the broader open science movement in academia (McKiernan et al., 2016) and wider industry trends (Eghbal, 2016). Importantly, FOSSS is typically developed by working scientists (not professional software developers), which sets up a precarious situation given the nature of the typical academic workplace wherein academics, especially in their early careers, are on short- and fixed-term contracts. In this paper, we argue that the existing ecosystem of neuroscientific open-source software is brittle, and discuss why and how the neuroscience community needs to come together to ensure a healthy software ecosystem to the benefit of all.
- 2 May 2025
- Published by MIT Press in Imaging Neuroscience
- Vol. 3
Open AccessCycling on the Freeway: The perilous state of open-source neuroscience software
Most scientists need software to perform their research (Barker et al., 2020; Carver et al., 2022; Hettrick, 2014; Hettrick et al., 2014; Switters & Osimo, 2019), and neuroscientists are no exception. Whether we work with reaction times, electrophysiological signals, or magnetic resonance imaging data, we rely on software to acquire, analyze, and statistically evaluate the raw data we obtain—or to generate such data if we work with simulations. In recent years, there has been a shift toward relying on free, open-source scientific software (FOSSS) for neuroscience data analysis (Poldrack et al., 2019), in line with the broader open science movement in academia (McKiernan et al., 2016) and wider industry trends (Eghbal, 2016). Importantly, FOSSS is typically developed by working scientists (not professional software developers), which sets up a precarious situation given the nature of the typical academic workplace wherein academics, especially in their early careers, are on short- and fixed-term contracts. In this paper, we argue that the existing ecosystem of neuroscientific open-source software is brittle, and discuss why and how the neuroscience community needs to come together to ensure a healthy software ecosystem to the benefit of all.
- Open Access
How forgiving are M/EEG inverse solutions to noise level misspecification? An excursion into the BSI-Zoo
A bstract: Brain source imaging (BSI), also known as source localization, from magneto- and electroencephalographic (M/EEG) data, is a challenging ill-posed inverse problem. Accurate source estimation is sensitive to modeling parameters, such as regularization strength and noise level, where misconfigurations can lead to under- or overfitting. Different BSI methods, however, may vary in their robustness to suboptimal parameter choices. Here we conducted extensive simulations of brain sources superimposed by varying degrees of sensor noise to study the ranges of noise misspecification within which different BSI approaches can still localize well. Using the Earth Mover’s Distance (EMD) and other metrics, we compare the performance of smooth linear inverse solutions with that of sparse non-linear Bayesian learning solutions. Additionally, we assess the effectiveness of various noise estimation and cross-validation techniques to select hyperparameters close to those achieving optimal localization. Methods and experiments are made available within the BSI-Zoo Python package.
Open AccessHow forgiving are M/EEG inverse solutions to noise level misspecification? An excursion into the BSI-Zoo
A bstract: Brain source imaging (BSI), also known as source localization, from magneto- and electroencephalographic (M/EEG) data, is a challenging ill-posed inverse problem. Accurate source estimation is sensitive to modeling parameters, such as regularization strength and noise level, where misconfigurations can lead to under- or overfitting. Different BSI methods, however, may vary in their robustness to suboptimal parameter choices. Here we conducted extensive simulations of brain sources superimposed by varying degrees of sensor noise to study the ranges of noise misspecification within which different BSI approaches can still localize well. Using the Earth Mover’s Distance (EMD) and other metrics, we compare the performance of smooth linear inverse solutions with that of sparse non-linear Bayesian learning solutions. Additionally, we assess the effectiveness of various noise estimation and cross-validation techniques to select hyperparameters close to those achieving optimal localization. Methods and experiments are made available within the BSI-Zoo Python package.
- Open Access
Multi-Source and Test-Time Domain Adaptation on Multivariate Signals using Spatio-Temporal Monge Alignment
Machine learning applications on signals such as computer vision or biomedical data often face significant challenges due to the variability that exists across hardware devices or session recordings. This variability poses a Domain Adaptation (DA) problem, as training and testing data distributions often differ. In this work, we propose Spatio-Temporal Monge Alignment (STMA) to mitigate these variabilities. This Optimal Transport (OT) based method adapts the cross-power spectrum density (cross-PSD) of multivariate signals by mapping them to the Wasserstein barycenter of source domains (multi-source DA). Predictions for new domains can be done with a filtering without the need for retraining a model with source data (test-time DA). We also study and discuss two special cases of the method, Temporal Monge Alignment (TMA) and Spatial Monge Alignment (SMA). Non-asymptotic concentration bounds are derived for the mappings estimation, which reveals a bias-plus-variance error structure with a variance decay rate of $\mathcal{O}(n_\ell^{-1/2})$ with $n_\ell$ the signal length. This theoretical guarantee demonstrates the efficiency of the proposed computational schema. Numerical experiments on multivariate biosignals and image data show that STMA leads to significant and consistent performance gains between datasets acquired with very different settings. Notably, STMA is a pre-processing step complementary to state-of-the-art deep learning methods.Open AccessMulti-Source and Test-Time Domain Adaptation on Multivariate Signals using Spatio-Temporal Monge Alignment
Machine learning applications on signals such as computer vision or biomedical data often face significant challenges due to the variability that exists across hardware devices or session recordings. This variability poses a Domain Adaptation (DA) problem, as training and testing data distributions often differ. In this work, we propose Spatio-Temporal Monge Alignment (STMA) to mitigate these variabilities. This Optimal Transport (OT) based method adapts the cross-power spectrum density (cross-PSD) of multivariate signals by mapping them to the Wasserstein barycenter of source domains (multi-source DA). Predictions for new domains can be done with a filtering without the need for retraining a model with source data (test-time DA). We also study and discuss two special cases of the method, Temporal Monge Alignment (TMA) and Spatial Monge Alignment (SMA). Non-asymptotic concentration bounds are derived for the mappings estimation, which reveals a bias-plus-variance error structure with a variance decay rate of $\mathcal{O}(n_\ell^{-1/2})$ with $n_\ell$ the signal length. This theoretical guarantee demonstrates the efficiency of the proposed computational schema. Numerical experiments on multivariate biosignals and image data show that STMA leads to significant and consistent performance gains between datasets acquired with very different settings. Notably, STMA is a pre-processing step complementary to state-of-the-art deep learning methods. - Open Access
Convolutional Monge Mapping Normalization for learning on sleep data
In many machine learning applications on signals and biomedical data, especially electroencephalogram (EEG), one major challenge is the variability of the data across subjects, sessions, and hardware devices. In this work, we propose a new method called Convolutional Monge Mapping Normalization (CMMN), which consists in filtering the signals in order to adapt their power spectrum density (PSD) to a Wasserstein barycenter estimated on training data. CMMN relies on novel closed-form solutions for optimal transport mappings and barycenters and provides individual test time adaptation to new data without needing to retrain a prediction model. Numerical experiments on sleep EEG data show that CMMN leads to significant and consistent performance gains independent from the neural network architecture when adapting between subjects, sessions, and even datasets collected with different hardware. Notably our performance gain is on par with much more numerically intensive Domain Adaptation (DA) methods and can be used in conjunction with those for even better performances.
Open AccessConvolutional Monge Mapping Normalization for learning on sleep data
In many machine learning applications on signals and biomedical data, especially electroencephalogram (EEG), one major challenge is the variability of the data across subjects, sessions, and hardware devices. In this work, we propose a new method called Convolutional Monge Mapping Normalization (CMMN), which consists in filtering the signals in order to adapt their power spectrum density (PSD) to a Wasserstein barycenter estimated on training data. CMMN relies on novel closed-form solutions for optimal transport mappings and barycenters and provides individual test time adaptation to new data without needing to retrain a prediction model. Numerical experiments on sleep EEG data show that CMMN leads to significant and consistent performance gains independent from the neural network architecture when adapting between subjects, sessions, and even datasets collected with different hardware. Notably our performance gain is on par with much more numerically intensive Domain Adaptation (DA) methods and can be used in conjunction with those for even better performances.
- Open Access
L-C2ST: Local Diagnostics for Posterior Approximations in Simulation-Based Inference
Many recent works in simulation-based inference (SBI) rely on deep generative models to approximate complex, high-dimensional posterior distributions. However, evaluating whether or not these approximations can be trusted remains a challenge. Most approaches evaluate the posterior estimator only in expectation over the observation space. This limits their interpretability and is not sufficient to identify for which observations the approximation can be trusted or should be improved. Building upon the well-known classifier two-sample test (C2ST), we introduce L-C2ST, a new method that allows for a local evaluation of the posterior estimator at any given observation. It offers theoretically grounded and easy to interpret -- e.g. graphical -- diagnostics, and unlike C2ST, does not require access to samples from the true posterior. In the case of normalizing flow-based posterior estimators, L-C2ST can be specialized to offer better statistical power, while being computationally more efficient. On standard SBI benchmarks, L-C2ST provides comparable results to C2ST and outperforms alternative local approaches such as coverage tests based on highest predictive density (HPD). We further highlight the importance of local evaluation and the benefit of interpretability of L-C2ST on a challenging application from computational neuroscience.
Open AccessL-C2ST: Local Diagnostics for Posterior Approximations in Simulation-Based Inference
Many recent works in simulation-based inference (SBI) rely on deep generative models to approximate complex, high-dimensional posterior distributions. However, evaluating whether or not these approximations can be trusted remains a challenge. Most approaches evaluate the posterior estimator only in expectation over the observation space. This limits their interpretability and is not sufficient to identify for which observations the approximation can be trusted or should be improved. Building upon the well-known classifier two-sample test (C2ST), we introduce L-C2ST, a new method that allows for a local evaluation of the posterior estimator at any given observation. It offers theoretically grounded and easy to interpret -- e.g. graphical -- diagnostics, and unlike C2ST, does not require access to samples from the true posterior. In the case of normalizing flow-based posterior estimators, L-C2ST can be specialized to offer better statistical power, while being computationally more efficient. On standard SBI benchmarks, L-C2ST provides comparable results to C2ST and outperforms alternative local approaches such as coverage tests based on highest predictive density (HPD). We further highlight the importance of local evaluation and the benefit of interpretability of L-C2ST on a challenging application from computational neuroscience.
- Open Access
Do try this at home: Age prediction from sleep and meditation with large-scale low-cost mobile EEG
EEG is an established method for quantifying large-scale neuronal dynamics which enables diverse real-world biomedical applications including brain-computer interfaces, epilepsy monitoring and sleep staging. Advances in sensor technology have freed EEG from traditional laboratory settings, making low-cost ambulatory or at-home assessments of brain function possible. While ecologically valid brain assessments are becoming more practical, the impact of their reduced spatial resolution and susceptibility to noise remain to be investigated. This study set out to explore the potential of at-home EEG assessments for biomarker discovery using the brain age framework and four-channel consumer EEG data. We analyzed recordings from more than 5200 human subjects (18-81 years) during meditation and sleep, focusing on the age prediction task. With cross-validated R 2 scores between 0.3 - 0.5, prediction performance was within the range of results obtained by recent benchmarks focused on laboratory-grade EEG. While age prediction was successful from both meditation and sleep recordings, the latter led to higher performance. Analysis by sleep stage uncovered that N2-N3 stages contained most of the signal. When combined, EEG features extracted from all sleep stages gave the best performance, suggesting that the entire night of sleep contains valuable age-related information. Furthermore, model comparisons suggested that information was spread out across electrodes and frequencies, supporting the use of multivariate modeling approaches. Thanks to our unique dataset of longitudinal repeat sessions spanning 153 to 529 days from eight subjects, we finally evaluated the variability of EEG-based age predictions, showing that they reflect both trait- and state-like information. Overall, our results demonstrate that state-of-the-art machine learning approaches based on age prediction can be readily applied to real-world EEG recordings obtained during at-home sleep and meditation practice.
Open AccessDo try this at home: Age prediction from sleep and meditation with large-scale low-cost mobile EEG
EEG is an established method for quantifying large-scale neuronal dynamics which enables diverse real-world biomedical applications including brain-computer interfaces, epilepsy monitoring and sleep staging. Advances in sensor technology have freed EEG from traditional laboratory settings, making low-cost ambulatory or at-home assessments of brain function possible. While ecologically valid brain assessments are becoming more practical, the impact of their reduced spatial resolution and susceptibility to noise remain to be investigated. This study set out to explore the potential of at-home EEG assessments for biomarker discovery using the brain age framework and four-channel consumer EEG data. We analyzed recordings from more than 5200 human subjects (18-81 years) during meditation and sleep, focusing on the age prediction task. With cross-validated R 2 scores between 0.3 - 0.5, prediction performance was within the range of results obtained by recent benchmarks focused on laboratory-grade EEG. While age prediction was successful from both meditation and sleep recordings, the latter led to higher performance. Analysis by sleep stage uncovered that N2-N3 stages contained most of the signal. When combined, EEG features extracted from all sleep stages gave the best performance, suggesting that the entire night of sleep contains valuable age-related information. Furthermore, model comparisons suggested that information was spread out across electrodes and frequencies, supporting the use of multivariate modeling approaches. Thanks to our unique dataset of longitudinal repeat sessions spanning 153 to 529 days from eight subjects, we finally evaluated the variability of EEG-based age predictions, showing that they reflect both trait- and state-like information. Overall, our results demonstrate that state-of-the-art machine learning approaches based on age prediction can be readily applied to real-world EEG recordings obtained during at-home sleep and meditation practice.