Search Results for author:
Found 34 papers, 18 papers with code
The largest EEG-based BCI reproducibility study for open science: the MOABB benchmark
The significance of this study lies in its contribution to establishing a rigorous and transparent benchmark for BCI research, offering insights into optimal methodologies and highlighting the importance of reproducibility in driving advancements within the field.
S-JEPA: towards seamless cross-dataset transfer through dynamic spatial attention
Motivated by the challenge of seamless cross-dataset transfer in EEG signal processing, this article presents an exploratory study on the use of Joint Embedding Predictive Architectures (JEPAs).
Equivariant plug-and-play image reconstruction
Plug-and-play algorithms constitute a popular framework for solving inverse imaging problems that rely on the implicit definition of an image prior via a denoiser.
Meta-Prior: Meta learning for Adaptive Inverse Problem Solvers
They are typically trained for a specific task, with a supervised loss to learn a mapping from the observations to the image to recover.
PAVI: Plate-Amortized Variational Inference
Given observed data and a probabilistic generative model, Bayesian inference searches for the distribution of the model's parameters that could have yielded the data.
Test like you Train in Implicit Deep Learning
Implicit deep learning has recently gained popularity with applications ranging from meta-learning to Deep Equilibrium Networks (DEQs).
Sliced-Wasserstein on Symmetric Positive Definite Matrices for M/EEG Signals
When dealing with electro or magnetoencephalography records, many supervised prediction tasks are solved by working with covariance matrices to summarize the signals.
A Lower Bound and a Near-Optimal Algorithm for Bilevel Empirical Risk Minimization
Bilevel optimization problems, which are problems where two optimization problems are nested, have more and more applications in machine learning.
FaDIn: Fast Discretized Inference for Hawkes Processes with General Parametric Kernels
Temporal point processes (TPP) are a natural tool for modeling event-based data.
Data augmentation for learning predictive models on EEG: a systematic comparison
Our experiments also show that there is no single best augmentation strategy, as the good augmentations differ on each task.
Benchopt: Reproducible, efficient and collaborative optimization benchmarks
Numerical validation is at the core of machine learning research as it allows to assess the actual impact of new methods, and to confirm the agreement between theory and practice.
PAVI: Plate-Amortized Variational Inference
Given some observed data and a probabilistic generative model, Bayesian inference aims at obtaining the distribution of a model's latent parameters that could have yielded the data.
Deep invariant networks with differentiable augmentation layers
Practitioners can typically enforce a desired invariance on the trained model through the choice of a network architecture, e. g. using convolutions for translations, or using data augmentation.
A framework for bilevel optimization that enables stochastic and global variance reduction algorithms
However, computing the gradient of the value function involves solving a linear system, which makes it difficult to derive unbiased stochastic estimates.
DriPP: Driven Point Processes to Model Stimuli Induced Patterns in M/EEG Signals
We derive a fast and principled expectation-maximization (EM) algorithm to estimate the parameters of this model.
CADDA: Class-wise Automatic Differentiable Data Augmentation for EEG Signals
Data augmentation is a key element of deep learning pipelines, as it informs the network during training about transformations of the input data that keep the label unchanged.
Understanding approximate and unrolled dictionary learning for pattern recovery
Dictionary learning consists of finding a sparse representation from noisy data and is a common way to encode data-driven prior knowledge on signals.
SHINE: SHaring the INverse Estimate from the forward pass for bi-level optimization and implicit models
In Deep Equilibrium Models (DEQs), the training is performed as a bi-level problem, and its computational complexity is partially driven by the iterative inversion of a huge Jacobian matrix.
HNPE: Leveraging Global Parameters for Neural Posterior Estimation
Inferring the parameters of a stochastic model based on experimental observations is central to the scientific method.
NeuMiss networks: differentiable programming for supervised learning with missing values.
We provide an upper bound on the Bayes risk of NeuMiss networks, and show that they have good predictive accuracy with both a number of parameters and a computational complexity independent of the number of missing data patterns.
Learning to solve TV regularised problems with unrolled algorithms
In this paper, we accelerate such iterative algorithms by unfolding proximal gradient descent solvers in order to learn their parameters for 1D TV regularized problems.
Extraction of Nystagmus Patterns from Eye-Tracker Data with Convolutional Sparse Coding
The analysis of the Nystagmus waveforms from eye-tracking records is crucial for the clinicial interpretation of this pathological movement.
Learning to solve TV regularized problems with unrolled algorithms
In this paper, we accelerate such iterative algorithms by unfolding proximal gradient descent solvers in order to learn their parameters for 1D TV regularized problems.
NeuMiss networks: differentiable programming for supervised learning with missing values
We provide an upper bound on the Bayes risk of NeuMiss networks, and show that they have good predictive accuracy with both a number of parameters and a computational complexity independent of the number of missing data patterns.
Super-efficiency of automatic differentiation for functions defined as a minimum
In most cases, the minimum has no closed-form, and an approximation is obtained via an iterative algorithm.
Learning step sizes for unfolded sparse coding
We demonstrate that for a large class of unfolded algorithms, if the algorithm converges to the solution of the Lasso, its last layers correspond to ISTA with learned step sizes.
Distributed Convolutional Dictionary Learning (DiCoDiLe): Pattern Discovery in Large Images and Signals
This algorithm can be used to distribute the computation on a number of workers which scales linearly with the encoded signal's size.
DICOD: Distributed Convolutional Coordinate Descent for Convolutional Sparse Coding
In this paper, we introduce DICOD, a convolutional sparse coding algorithm which builds shift invariant representations for long signals.
Multivariate Convolutional Sparse Coding for Electromagnetic Brain Signals
Frequency-specific patterns of neural activity are traditionally interpreted as sustained rhythmic oscillations, and related to cognitive mechanisms such as attention, high level visual processing or motor control.
Post-training for Deep Learning
One of the main challenges of deep learning methods is the choice of an appropriate training strategy.
Understanding the Learned Iterative Soft Thresholding Algorithm with matrix factorization
Sparse coding is a core building block in many data analysis and machine learning pipelines.
DICOD: Distributed Convolutional Sparse Coding
In this paper, we introduce DICOD, a convolutional sparse coding algorithm which builds shift invariant representations for long signals.
Post Training in Deep Learning with Last Kernel
One of the main challenges of deep learning methods is the choice of an appropriate training strategy.
Understanding Trainable Sparse Coding via Matrix Factorization
Sparse coding is a core building block in many data analysis and machine learning pipelines.
