10 citations · 21 across the 7 of their papers we have counts for
9 papers
Towards Universal Wasserstein Barycenters through Flow Matching
Eduardo Fernandes Montesuma
Defining a weighted mean over probability measures under probability metrics is a central tool in probabilistic machine learning. Under the Wasserstein metric, these are called \em…
KDM: A unifying framework for feature knowledge distillation
Eduardo Fernandes Montesuma
Knowledge Distillation (KD) seeks to transfer the knowledge of a teacher, towards a student neural net. This process is often done by matching the networks' predictions (i.e., thei…
Unsupervised Anomaly Detection through Mass Repulsing Optimal Transport
Eduardo Fernandes Montesuma, Adel El Habazi, Fred Ngole Mboula
Detecting anomalies in datasets is a longstanding problem in machine learning. In this context, anomalies are defined as a sample that significantly deviates from the remaining dat…
Lighter, Better, Faster Multi-Source Domain Adaptation with Gaussian Mixture Models and Optimal Transport
Eduardo Fernandes Montesuma, Fred Ngolè Mboula, Antoine Souloumiac
In this paper, we tackle Multi-Source Domain Adaptation (MSDA), a task in transfer learning where one adapts multiple heterogeneous, labeled source probability measures towards a d…
Optimal Transport for Domain Adaptation through Gaussian Mixture Models
Eduardo Fernandes Montesuma, Fred Maurice Ngolè Mboula, Antoine Souloumiac
Machine learning systems operate under the assumption that training and test data are sampled from a fixed probability distribution. However, this assumptions is rarely verified in…
Benchmarking Domain Adaptation for Chemical Processes on the Tennessee Eastman Process
Eduardo Fernandes Montesuma, Michela Mulas, Fred Ngolè Mboula +2
In system monitoring, automatic fault diagnosis seeks to infer the systems' state based on sensor readings, e.g., through machine learning models. In this context, it is of key imp…
Multi-Source Domain Adaptation through Dataset Dictionary Learning in Wasserstein Space
Eduardo Fernandes Montesuma, Fred Ngolè Mboula, Antoine Souloumiac
This paper seeks to solve Multi-Source Domain Adaptation (MSDA), which aims to mitigate data distribution shifts when transferring knowledge from multiple labeled source domains to…
Recent Advances in Optimal Transport for Machine Learning
Eduardo Fernandes Montesuma, Fred Ngolè Mboula, Antoine Souloumiac
Recently, Optimal Transport has been proposed as a probabilistic framework in Machine Learning for comparing and manipulating probability distributions. This is rooted in its rich…
OpenDenoising: an Extensible Benchmark for Building Comparative Studies of Image Denoisers
Florian Lemarchand, Eduardo Fernandes Montesuma, Maxime Pelcat +1
Image denoising has recently taken a leap forward due to machine learning. However, image denoisers, both expert-based and learning-based, are mostly tested on well-behaved generat…