Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Damaskinos, Georgios"'
Autor:
Solbiati, Alessandro, Heffernan, Kevin, Damaskinos, Georgios, Poddar, Shivani, Modi, Shubham, Cali, Jacques
Topic segmentation of meetings is the task of dividing multi-person meeting transcripts into topic blocks. Supervised approaches to the problem have proven intractable due to the difficulties in collecting and accurately annotating large datasets. In
Externí odkaz:
http://arxiv.org/abs/2106.12978
Autor:
Damaskinos, Georgios, Guerraoui, Rachid, Kermarrec, Anne-Marie, Nitu, Vlad, Patra, Rhicheek, Taiani, Francois
Federated Learning (FL) is very appealing for its privacy benefits: essentially, a global model is trained with updates computed on mobile devices while keeping the data of users local. Standard FL infrastructures are however designed to have no ener
Externí odkaz:
http://arxiv.org/abs/2006.07273
Autor:
Damaskinos, Georgios, Mendler-Dünner, Celestine, Guerraoui, Rachid, Papandreou, Nikolaos, Parnell, Thomas
In this paper we tackle the challenge of making the stochastic coordinate descent algorithm differentially private. Compared to the classical gradient descent algorithm where updates operate on a single model vector and controlled noise addition to t
Externí odkaz:
http://arxiv.org/abs/2006.07272
Asynchronous distributed machine learning solutions have proven very effective so far, but always assuming perfectly functioning workers. In practice, some of the workers can however exhibit Byzantine behavior, caused by hardware failures, software b
Externí odkaz:
http://arxiv.org/abs/1802.07928
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Damaskinos, Georgios, Guerraoui, Rachid, Kermarrec, Anne-Marie, Nitu, Vlad-Tiberiu, Patra, Rhicheek, Taïani, François
Publikováno v:
Middleware 2020-ACM/IFIP 21st International Middleware conference
Middleware 2020-ACM/IFIP 21st International Middleware conference, Dec 2020, Delft / Virtual, Netherlands
Middleware 2020-ACM/IFIP 21st International Middleware conference, Dec 2020, Delft / Virtual, Netherlands
International audience; Existing approaches to distribute Generative Adversarial Networks (GANs) either (i) fail to scale for they typically put the two components of a GAN (the generator and the discriminator) on different machines, inducing signifi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::2ef558032a0dec4d7a85173d65c1a8d5
https://hal.inria.fr/hal-03043237/document
https://hal.inria.fr/hal-03043237/document
Autor:
Damaskinos, Georgios
The ever-growing number of edge devices (e.g., smartphones) and the exploding volume of sensitive data they produce, call for distributed machine learning techniques that are privacy-preserving. Given the increasing computing capabilities of modern e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b7ccd82d81904589d5813ce314fea3d0
Autor:
Cohn-Gordon, Katriel, Damaskinos, Georgios, Neto, Divino, Cordova, Shi, Reitz, Benoit, Strahs, Benjamin, Obenshain, Daniel, Pearce, Paul, Papagiannis, Loannis
Deletion is a core facet of Online Social Networks (OSNs). For users, deletion is a tool to remove what they have shared and control their data. For OSNs, robust deletion is both an obligation to their users and a risk when developer mistakes inevita
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______185::dd8589f07a8be71401a0038ca97258d6
https://infoscience.epfl.ch/record/287859
https://infoscience.epfl.ch/record/287859
Autor:
Damaskinos, Georgios, El Mhamdi, El Mahdi, Guerraoui, Rachid, Guirguis, Arsany Hany Abdelmessih, Rouault, Sébastien Louis Alexandre
We present AGGREGATHOR, a framework that implements state-of-the-art robust (Byzantine-resilient) distributed stochastic gradient descent. Following the standard parameter server model, we assume that a minority of worker machines can be controlled b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______185::803f930c8856ba090afd07ad7f6f9740
https://infoscience.epfl.ch/record/265684
https://infoscience.epfl.ch/record/265684