Mokhtar Z. Alaya
Statut : Maître de Conférences
Bureau : GI 133
I am Assistant Professor of Statistics and Machine Learning at University of Technology of Compiègne (UTC). I teach in the computer sciences department (GI) and I do my research in the laboratory of applied mathematics (LMAC). You can visit my Github page https://mzalaya.github.io to access to all my publications.
Travaux récents
Adversarial Semi-Supervised Domain Adaptation for Semantic Segmentation : A New Role for Labeled Target Samples, Preprint, 2024, (arXiv)
Neutron Spectrum Unfolding using two Architectures of Convolutional Neural Networks, Nuclear Engineering and Technology, 2023, (Journal)
Optimal transport for conditional domain matching and label shift, Machine Learning, 2021, (Journal)
Statistical and Topological Properties of Gaussian Smoothed Sliced Probability Divergences, Preprint, 2021, (arXiv)
Heterogeneous Wasserstein Discrepancy for Incomparable Distributions, Preprint, 2021, (arXiv)
Theoretical Guarantees for Bridging Metric Measure Embedding and Optimal Transport, Neurocomputing, 2021, (Journal)
Optimal Transport for Conditional Domain Matching and Label Shift, Machine Learning, 2021, (Journal)
Binacox : Automatic Cut-Point Detection in High-dimensional Cox Model with Applications in Genetics, Biometrics, 2021, (Journal)
POT : Python Optimal Transport, Journal of Machine Learning Research, 2020, (Journal)
Partial Optimal Transport with Application on Positive-Unlabeled Learning, Proceedings Conference NeurIPS, 2020, (Conference)
Open Set Domain Adaptation using Optimal Transport, Proceedings Conference ECML-PKDD, 2020, (Conference)
Screening Sinkhorn Algorithm for Regularized Optimal Transport, Proceedings Conference NeurIPS, 2019, (Conference)