Skip to Main content Skip to Navigation
New interface

Estimation robuste des modèles de mélange sur des données distribuées

Abstract : This work proposes a contribution aiming at probabilistic model estimation, in the setting of dis- tributed, decentralized, data-sharing computer systems. Such systems are developing over the in- ternet, and also exist as sensor networks, for instance. Our general goal consists in estimating a probability distribution over a data set which is distributed into subsets located on the nodes of a distributed system. More precisely, we are at estimating the global distribution by aggregating local distributions, estimated on these local subsets. Our proposal exploits the following assumption: all distributions are modelled as a Gaussian mixture. Our contribution is a solution that is both decen- tralized and statistically robust to outlier local Gaussian mixture models. The proposed process only requires mixture parameters, rather than original data.
Document type :
Complete list of metadata

Cited literature [138 references]  Display  Hide  Download
Contributor : Marc Gelgon Connect in order to contact the contributor
Submitted on : Saturday, October 27, 2012 - 12:12:35 PM
Last modification on : Wednesday, April 27, 2022 - 4:11:15 AM
Long-term archiving on: : Saturday, December 17, 2016 - 6:25:21 AM


  • HAL Id : tel-00746118, version 1


Ali El Attar. Estimation robuste des modèles de mélange sur des données distribuées. Apprentissage [cs.LG]. Université de Nantes, 2012. Français. ⟨NNT : ⟩. ⟨tel-00746118⟩



Record views


Files downloads