Publications

Machine Learning

Learning to Rank Anomalies: Scalar Performance Criteria and Maximization of Two-Sample Rank Statistics

The ability to collect and store ever more massive databases has been accompanied by the need to process them efficiently. In many cases, most observations have the same behavior, while a probable small proportion of these observations are abnormal…

Myrto Limnios, Nathan Noiry, Stéphan Clémençon

Proceedings of the Third International Workshop on Learning with Imbalanced Domains: Theory and Applications (2021) - 2021

Statistics

Adversarial Weighting for Domain Adaptation in Regression

We present a novel instance-based approach to handle regression tasks in the context of supervised domain adaptation under an assumption of covariate shift. The approach developed in this paper is based on the assumption that the task on the target…

Antoine de Mathelin, Guillaume Richard, François Deheeger, Mathilde Mougeot, Nicolas Vayatis

2021 IEEE 33rd International Conference on Tools with Artificial Intelligence (ICTAI) - 2021

Computer Science and Game Theory

Sequential Learning in a strategical environment

In sequential learning (or repeated games), data is acquired and treated on the fly and an algorithm (or strategy) learns to behave as well as if it got in hindsight the state of nature, e.g., distributions of rewards. In many real life scenarios,…

Etienne Boursier

Machine Learning

Concentration Inequalities for Two-Sample Rank Processes with Application to Bipartite Ranking

The ROC curve is the gold standard for measuring the performance of a test/scoring statistic regarding its capacity to discriminate between two statistical populations in a wide variety of applications, ranging from anomaly detection in signal…

Stéphan Clémençon, Myrto Limnios, Nicolas Vayatis

Electronic Journal of Statistics - 2021

Modeling and Simulation

Numerical method for the computation of first-arrival time of seismic waves with general anisotropy

We present a numerical method for computing the first arrival time of seismic waves. The scheme can tackle three dimensional media with elastic properties defined by a fully anisotropic Hooke tensor. Our numerical method proceeds in a single pass…

François Desquilbet, Ludovic Métivier, Jean-Marie Mirebeau

First International Meeting for Applied Geoscience & Energy - 2021

Life Sciences

Receptor Tyrosine Kinase KIT: A New Look for an Old Receptor

Receptor tyrosine kinases (RTKs) control various signalling pathways in cells. Their remarkable conformational plasticity enables the specific recognition of many molecules such as ligands, substrates or proteins. In solution, RTKs are in…

Tchertanov L & Ledoux, Julie Ledoux

The 3rd Struchkov Meeting (2021) – Struchkov Prize Society (struchkovprizeassociation.org) - 2021

Engineering Sciences

Surrogate model based approach to predict fatigue stress field in multi-stranded cables

A. Belkhabbaz, M. Gueguin, F. Hafid, C. Yang, O. Allix, Jean-Michel Ghidaglia

International Journal of Solids and Structures - 2021

Probability

On quantitative Laplace-type convergence results for some exponential probability measures, with two applications

Laplace-type results characterize the limit of sequence of measures (πε)ε>0 with density w.r.t the Lebesgue measure (dπε/dλ)(x) ∝ exp[−U (x)/ε] when the temperature ε > 0 converges to 0. If a limiting distribution π0 exists, it concentrates on…

Valentin de Bortoli, Agnès Desolneux

Statistics

High dimensional pattern learning applied to symbolic time-series

Bien que l'adoption de l'apprentissage automatique dans de nombreux contextes appliqués ait connu une croissance rapide au cours de la dernière décennie, son utilisation dans certains environnements industriels reste problématique. La raison…

Amir Dib

Human-Computer Interaction

La Réalité Virtuelle au service de la conception architecturale participative : une étude exploratoire

La conception architecturale constitue un domaine d’intervention complexe pour l’ergonomie. En particulier, de nombreux auteurs et praticiens s’interrogent sur les meilleures manières de faire pour intégrer une perspective centrée sur l’activité…

Clémence Fandard, Matilde Lima De Albuquerque, Jeanne Vezien, Stéphane Safin, Julien Nelson

ERGO'IA 2021 - 2021