Émilie Devijver
YOU?
Author Swipe
Relaxing partition admissibility in Cluster-DAGs: a causal calculus with arbitrary variable clustering Open
Cluster DAGs (C-DAGs) provide an abstraction of causal graphs in which nodes represent clusters of variables, and edges encode both cluster-level causal relationships and dependencies arisen from unobserved confounding. C-DAGs define an eq…
DNA methylation and immune infiltration mediate the impact of tobacco exposure on pancreatic adenocarcinoma outcome: a high-dimensional mediation analysis Open
Pancreatic ductal adenocarcinoma (PDAC) ranks among the most aggressive malignancies, characterized by exceptionally poor prognosis due to late diagnosis and therapeutic resistance. While tobacco exposure is an established risk factor for …
Identifiability in Causal Abstractions: A Hierarchy of Criteria Open
Identifying the effect of a treatment from observational data typically requires assuming a fully specified causal diagram. However, such diagrams are rarely known in practice, especially in complex or high-dimensional settings. To overcom…
Identifiability by common backdoor in summary causal graphs of time series Open
The identifiability problem for interventions aims at assessing whether the total effect of some given interventions can be written with a do-free formula, and thus be computed from observational data only. We study this problem, consideri…
Complete Characterization for Adjustment in Summary Causal Graphs of Time Series Open
The identifiability problem for interventions aims at assessing whether the total causal effect can be written with a do-free formula, and thus be estimated from observational data only. We study this problem, considering multiple interven…
Some recent developments on functional data analysis Open
Recent contributions to functional data analysis are presented. Various problems are considered including the definition of the barycenter of multivariate functional data and the adaptive nonparametric estimation in the functional linear m…
On the Fly Detection of Root Causes from Observed Data with Application to IT Systems Open
International audience
Efficient Initial Data Selection and Labeling for Multi-Class Classification Using Topological Analysis Open
Machine learning techniques often require large labeled training sets to attain optimal performance. However, acquiring labeled data can pose challenges in practical scenarios. Pool-based active learning methods aim to select the most rele…
Ensembles of Probabilistic Regression Trees Open
Tree-based ensemble methods such as random forests, gradient-boosted trees, and Bayesianadditive regression trees have been successfully used for regression problems in many applicationsand research studies. In this paper, we study ensembl…
Stable network inference in high-dimensional graphical model using single-linkage Open
Stability, akin to reproducibility, is crucial in statistical analysis. This paper examines the stability of sparse network inference in high-dimensional graphical models, where selected edges should remain consistent across different samp…
Should we correct the bias in Confidence Bands for Repeated Functional Data? Open
While confidence intervals for finite quantities are well-established, constructing confidence bands for objects of infinite dimension, such as functions, poses challenges. In this paper, we explore the concept of parametric confidence ban…
Classification Tree-based Active Learning: A Wrapper Approach Open
Supervised machine learning often requires large training sets to train accurate models, yet obtaining large amounts of labeled data is not always feasible. Hence, it becomes crucial to explore active learning methods for reducing the size…
Informative Training Data for Efficient Property Prediction in Metal–Organic Frameworks by Active Learning Open
In recent data-driven approaches to material discovery, scenarios where target quantities are expensive to compute and measure are often overlooked. In such cases, it becomes imperative to construct a training set that includes the most di…
On the Fly Detection of Root Causes from Observed Data with Application to IT Systems Open
This paper introduces a new structural causal model tailored for representing threshold-based IT systems and presents a new algorithm designed to rapidly detect root causes of anomalies in such systems. When root causes are not causally re…
Mixture of segmentation for heterogeneous functional data Open
International audience
Feature Selection for High-Dimensional Neural Network Potentials with the Adaptive Group Lasso Open
Neural network potentials are a powerful tool for atomistic simulations, allowing to accurately reproduce \textit{ab initio} potential energy surfaces with computational performance approaching classical force fields. A central component o…
Informative Training Data for Efficient Property Prediction in Metal-Organic Frameworks by Active Learning Open
In recent data-driven approaches to materials discov- ery, scenarios where target quantities are expensive to compute or measure are often overlooked. In such cases, it becomes imperative to construct a training set that includes the most …
Identifiability of total effects from abstractions of time series causal graphs Open
We study the problem of identifiability of the total effect of an intervention from observational time series in the situation, common in practice, where one only has access to abstractions of the true causal graph. We consider here two ab…
Artificial Neural Network-Based Density Functional Approach for Adiabatic Energy Differences in Transition Metal Complexes Open
During the past decades, approximate Kohn-Sham density functional theory schemes have garnered many successes in computational chemistry and physics, yet the performance in the prediction of spin state energetics is often unsatisfactory. B…
Pool-Based Active Learning with Proper Topological Regions Open
Machine learning methods usually rely on large sample size to have good performance, while it is difficult to provide labeled set in many applications. Pool-based active learning methods are there to detect, among a set of unlabeled data, …
Survey and Evaluation of Causal Discovery Methods for Time Series (Extended Abstract) Open
We introduce in this survey the major concepts, models, and algorithms proposed so far to infer causal relations from observational time series, a task usually referred to as causal discovery in time series. To do so, after a description o…
Case Studies of Causal Discovery from IT Monitoring Time Series Open
Information technology (IT) systems are vital for modern businesses, handling data storage, communication, and process automation. Monitoring these systems is crucial for their proper functioning and efficiency, as it allows collecting ext…
Causal Discovery from Time Series with Hybrids of Constraint-Based and Noise-Based Algorithms Open
Constraint-based methods and noise-based methods are two distinct families of methods proposed for uncovering causal graphs from observational data. However, both operate under strong assumptions that may be challenging to validate or coul…
An Artificial Neural Network-based Density Functional Approach for Adiabatic Energy Differences in Transition Metal Complexes Open
During the past decades, approximate Kohn-Sham density-functional theory schemes garnered many successes in computational chemistry and physics; yet the performance in the prediction of spin state energetics is often unsatisfactory. By mea…
Mixture of segmentation for heterogeneous functional data Open
In this paper we consider functional data with heterogeneity in time and in population. We propose a mixture model with segmentation of time to represent this heterogeneity while keeping the functional structure. Maximum likelihood estimat…
Crystal Nucleation in Al-Ni Alloys: an Unsupervised Chemical and Topological Learning Approach Open
Crystallization represents a fundamental process engendering solidification of a material and determines its microstructure. Driven by complex phenomena at the atomic scale, its understanding for alloys still remains elusive. The present w…
A Conditional Mutual Information Estimator for Mixed Data and an Associated Conditional Independence Test Open
In this study, we focus on mixed data which are either observations of univariate random variables which can be quantitative or qualitative, or observations of multivariate random variables such that each variable can include both quantita…
Entropy-Based Discovery of Summary Causal Graphs in Time Series Open
This study addresses the problem of learning a summary causal graph on time series with potentially different sampling rates. To do so, we first propose a new causal temporal mutual information measure for time series. We then show how thi…