activity
20152025
collaborators

11 papers

cs.LG2025

PatchTrAD: A Patch-Based Transformer focusing on Patch-Wise Reconstruction Error for Time Series Anomaly Detection

Samy-Melwan Vilhes, Gilles Gasso, Mokhtar Z Alaya

Time series anomaly detection (TSAD) focuses on identifying whether observations in streaming data deviate significantly from normal patterns. With the prevalence of connected devi…

cs.CV2023

Adversarial Semi-Supervised Domain Adaptation for Semantic Segmentation: A New Role for Labeled Target Samples

Marwa Kechaou, Mokhtar Z. Alaya, Romain Hérault +1

Adversarial learning baselines for domain adaptation (DA) approaches in the context of semantic segmentation are under explored in semi-supervised framework. These baselines involv…

cs.LG2021

Statistical and Topological Properties of Gaussian Smoothed Sliced Probability Divergences

Alain Rakotomamonjy, Mokhtar Z. Alaya, Maxime Berar +1

Gaussian smoothed sliced Wasserstein distance has been recently introduced for comparing probability distributions, while preserving privacy on the data. It has been shown, in appl…

cs.LG2020

Open Set Domain Adaptation using Optimal Transport

Marwa Kechaou, Romain Hérault, Mokhtar Z. Alaya +1

We present a 2-step optimal transport approach that performs a mapping from a source distribution to a target distribution. Here, the target has the particularity to present new cl…

cs.LG2020

Optimal Transport for Conditional Domain Matching and Label Shift

Alain Rakotomamonjy, Rémi Flamary, Gilles Gasso +3

We address the problem of unsupervised domain adaptation under the setting of generalized target shift (joint class-conditional and label shifts). For this framework, we theoretica…

stat.ML2020

Theoretical Guarantees for Bridging Metric Measure Embedding and Optimal Transport

Mokhtar Z. Alaya, Maxime Bérar, Gilles Gasso +1

We propose a novel approach for comparing distributions whose supports do not necessarily lie on the same metric space. Unlike Gromov-Wasserstein (GW) distance which compares pairw…