Stéphane Chrétien
YOU?
Author Swipe
View article: Conformal Online Learning of Deep Koopman Linear Embeddings
Conformal Online Learning of Deep Koopman Linear Embeddings Open
We introduce Conformal Online Learning of Koopman embeddings (COLoKe), a novel framework for adaptively updating Koopman-invariant representations of nonlinear dynamical systems from streaming data. Our modeling approach combines deep feat…
View article: Tukey-Median of Means-Gradients for Langevin Dynamics: a Robust Approach to Fitting Machine Learning Models
Tukey-Median of Means-Gradients for Langevin Dynamics: a Robust Approach to Fitting Machine Learning Models Open
Median-of-Means (MoM) estimators have emerged as powerful tools for robust learning when data are corrupted by outliers or exhibit heavy-tailed distributions. However, incorporating MoM principles to design robust loss functions typically …
View article: SigBERT: Combining Narrative Medical Reports and Rough Path Signature Theory for Survival Risk Estimation in Oncology
SigBERT: Combining Narrative Medical Reports and Rough Path Signature Theory for Survival Risk Estimation in Oncology Open
Electronic medical reports (EHR) contain a vast amount of information that can be leveraged for machine learning applications in healthcare. However, existing survival analysis methods often struggle to effectively handle the complexity of…
View article: Detecting malignant dynamics on very few blood sample using signature coefficients
Detecting malignant dynamics on very few blood sample using signature coefficients Open
Recent discoveries have suggested that the promising avenue of using circulating tumor DNA (ctDNA) levels in blood samples provides reasonable accuracy for cancer monitoring, with extremely low burden on the patient's side. It is known tha…
View article: Optimized Spectral Clustering Methods For Potentially Divergent Biological Sequences
Optimized Spectral Clustering Methods For Potentially Divergent Biological Sequences Open
Various recent researches in bioinformatics demonstrated that clustering is a very efficient technique for sequence analysis. Spectral clustering is particularly efficient for highly divergent sequences and GMMs (Gaussian Mixture Models) a…
View article: Time topological analysis of EEG using signature theory
Time topological analysis of EEG using signature theory Open
Anomaly detection in multivariate signals is a task of paramount importance in many disciplines (epidemiology, finance, cognitive sciences and neurosciences, oncology, etc.). In this perspective, Topological Data Analysis (TDA) offers a ba…
View article: A mixture of experts regression model for functional response with functional covariates
A mixture of experts regression model for functional response with functional covariates Open
Due to the fast growth of data that are measured on a continuous scale, functional data analysis has undergone many developments in recent years. Regression models with a functional response involving functional covariates, also called "fu…
View article: Registration of algebraic varieties using Riemannian optimization
Registration of algebraic varieties using Riemannian optimization Open
We consider the point cloud registration problem, the task of finding a transformation between two point clouds that represent the same object but are expressed in different coordinate systems. Our approach is not based on a point-to-point…
View article: Convergence and scaling of Boolean-weight optimization for hardware reservoirs
Convergence and scaling of Boolean-weight optimization for hardware reservoirs Open
Hardware implementation of neural network are an essential step to implement next generation efficient and powerful artificial intelligence solutions. Besides the realization of a parallel, efficient and scalable hardware architecture, the…
View article: An SDP Dual Relaxation for the Robust Shortest-Path Problem with Ellipsoidal Uncertainty: Pierra’s Decomposition Method and a New Primal Frank–Wolfe-Type Heuristics for Duality Gap Evaluation
An SDP Dual Relaxation for the Robust Shortest-Path Problem with Ellipsoidal Uncertainty: Pierra’s Decomposition Method and a New Primal Frank–Wolfe-Type Heuristics for Duality Gap Evaluation Open
This work addresses the robust counterpart of the shortest path problem (RSPP) with a correlated uncertainty set. Because this problem is difficult, a heuristic approach, based on Frank–Wolfe’s algorithm named discrete Frank–Wolfe (DFW), h…
View article: Special Issue on Safe and Reliable AI for Smart Sustainable Cities
Special Issue on Safe and Reliable AI for Smart Sustainable Cities Open
Today, most of the world’s inhabitants live in cities [...]
View article: Fast Hyperparameter Calibration of Sparsity Enforcing Penalties in Total Generalised Variation Penalised Reconstruction Methods for XCT Using a Planted Virtual Reference Image
Fast Hyperparameter Calibration of Sparsity Enforcing Penalties in Total Generalised Variation Penalised Reconstruction Methods for XCT Using a Planted Virtual Reference Image Open
The reconstruction problem in X-ray computed tomography (XCT) is notoriously difficult in the case where only a small number of measurements are made. Based on the recently discovered Compressed Sensing paradigm, many methods have been pro…
View article: An SDP dual relaxation for the Robust Shortest Path Problem with ellipsoidal uncertainty: Pierra's decomposition method and a new primal Frank-Wolfe-type heuristics for duality gap evaluation
An SDP dual relaxation for the Robust Shortest Path Problem with ellipsoidal uncertainty: Pierra's decomposition method and a new primal Frank-Wolfe-type heuristics for duality gap evaluation Open
This work addresses the Robust counterpart of the Shortest Path Problem (RSPP) with a correlated uncertainty set. Since this problem is hard, a heuristic approach, based on Frank-Wolfe's algorithm named Discrete Frank-Wolf (DFW), has recen…
View article: Ant Colony-Based Hyperparameter Optimisation in Total Variation Reconstruction in X-ray Computed Tomography
Ant Colony-Based Hyperparameter Optimisation in Total Variation Reconstruction in X-ray Computed Tomography Open
In this paper, a computer-aided training method for hyperparameter selection of limited data X-ray computed tomography (XCT) reconstruction was proposed. The proposed method employed the ant colony optimisation (ACO) approach to assist in …
View article: Benign overfitting of fully connected Deep Nets:A Sobolev space viewpoint
Benign overfitting of fully connected Deep Nets:A Sobolev space viewpoint Open
Deep neural nets have undergone tremendous improvements in the last decade, which revolutionised the field of machine learning in a broad and lasting manner, achieving unprecedented performance in such diverse fields as image analysis, poi…
View article: A finite sample analysis of the double descent phenomenon for ridge function estimation.
A finite sample analysis of the double descent phenomenon for ridge function estimation. Open
Recent extensive numerical experiments in high scale machine learning have allowed to uncover a quite counterintuitive phase transition, as a function of the ratio between the sample size and the number of parameters in the model. As the n…
View article: A finite sample analysis of the benign overfitting phenomenon for ridge\n function estimation
A finite sample analysis of the benign overfitting phenomenon for ridge\n function estimation Open
Recent extensive numerical experiments in high scale machine learning have\nallowed to uncover a quite counterintuitive phase transition, as a function of\nthe ratio between the sample size and the number of parameters in the model. As\nth…
View article: A finite sample analysis of the benign overfitting phenomenon for ridge function estimation
A finite sample analysis of the benign overfitting phenomenon for ridge function estimation Open
Recent extensive numerical experiments in high scale machine learning have allowed to uncover a quite counterintuitive phase transition, as a function of the ratio between the sample size and the number of parameters in the model. As the n…
View article: Projection Methods for Uniformly Convex Expandable Sets
Projection Methods for Uniformly Convex Expandable Sets Open
Many problems in medical image reconstruction and machine learning can be formulated as nonconvex set theoretic feasibility problems. Among efficient methods that can be put to work in practice, successive projection algorithms have receiv…
View article: The dual approach to non-negative super-resolution: perturbation analysis
The dual approach to non-negative super-resolution: perturbation analysis Open
We study the problem of super-resolution, where we recover the locations and weights of non-negative point sources from a few samples of their convolution with a Gaussian kernel. It has been shown that exact recovery is possible by minimis…
View article: Boolean learning under noise-perturbations in hardware neural networks
Boolean learning under noise-perturbations in hardware neural networks Open
A high efficiency hardware integration of neural networks benefits from realizing nonlinearity, network connectivity and learning fully in a physical substrate. Multiple systems have recently implemented some or all of these operations, ye…
View article: Spectrally Sparse Tensor Reconstruction in Optical Coherence Tomography Using Nuclear Norm Penalisation
Spectrally Sparse Tensor Reconstruction in Optical Coherence Tomography Using Nuclear Norm Penalisation Open
Reconstruction of 3D objects in various tomographic measurements is an important problem which can be naturally addressed within the mathematical framework of 3D tensors. In Optical Coherence Tomography, the reconstruction problem can be r…
View article: Learning with Semi-Definite Programming: new statistical bounds based on\n fixed point analysis and excess risk curvature
Learning with Semi-Definite Programming: new statistical bounds based on\n fixed point analysis and excess risk curvature Open
Many statistical learning problems have recently been shown to be amenable to\nSemi-Definite Programming (SDP), with community detection and clustering in\nGaussian mixture models as the most striking instances [javanmard et al.,\n2016]. G…
View article: Learning with Semi-Definite Programming: new statistical bounds based on fixed point analysis and excess risk curvature
Learning with Semi-Definite Programming: new statistical bounds based on fixed point analysis and excess risk curvature Open
Many statistical learning problems have recently been shown to be amenable to Semi-Definite Programming (SDP), with community detection and clustering in Gaussian mixture models as the most striking instances [javanmard et al., 2016]. Give…