Bio
I am currently Maître de Conférences of Statistics and Machine Learning at Université de Technologie de Compiègne (UTC). I teach in Computer Science Department and I do my research in laboratory of Applied Mathematics (LMAC).
My research focuses on theoretical, algorithmic, and practical aspects of machine learning. It lies at the intersection of statistics, optimization, and computer science: statistics provides the foundations for modeling and theoretical guarantees; optimization drives the design of efficient algorithms; and computer science enables scalable and reliable implementation. Together, these three disciplines form the core of modern data science.
I am also interested in developing machine/deep learning models and algorithms for interdisciplinary applications in mechanics, chemistry, biomedical, etc.
If you are interested in collaborating with me, drop me an email or get in touch through one of the links at the top of the page.
News
-
Jun. 2026
Interdisciplinary Paper, Composites Multi-source Sensor Data Fusion Framework for Structural Health Monitoring of Polymer-Matrix Composites (PMC) Based on Latent-Space Clustering Using a Convolutional Autoencoder. Mechanics of Advanced Materials and Structures.
-
Apr. 2026
Paper. Optimal Transport Convergence of Conditional Distribution Estimation for Single-Indexed Locally Stationary Functional Time Series. Results in Applied Mathematics.
-
Apr. 2026
Paper. Bounds in Wasserstein Distance for Locally Stationary Functional Time Series. Computational Statistics.
-
Mar. 2026
Spotlight Paper. Does Normalization Choice Matter for Causal Large Time-Series Models? ICLR 2026 Workshop on Time Series in the Age of Large Models.
- Feb. 2026
-
Jan. 2026
Paper. A Unified Kantorovich Duality for Multimarginal Optimal Transport. Submitted.
-
Jan. 2026
Paper. Optimal Transport Guarantees to Nonparametric Regression for Locally Stationary Time Series. Artificial Intelligence and Statistics Conference, AISTATS 2026.
-
Jan. 2026
Paper. Unmixing Mean Embeddings for Domain Adaptation with Target Label Proportion. Artificial Intelligence and Statistics Conference, AISTATS 2026.
