Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.
AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.
Machine Learning (ML) solutions are nowadays distributed, according to the so-called server/worker architecture. One server holds the model parameters while several workers train the model. Clearly, such architecture is prone to various types of component ...
Association for Computing Machinery2020
, ,
We present GARFIELD, a library to transparently make machine learning (ML) applications, initially built with popular (but fragile) frameworks, e.g., TensorFlow and PyTorch, Byzantine–resilient. GARFIELD relies on a novel object–oriented design, reducing t ...
IEEE2021
, , ,
The likelihood function is a fundamental component in Bayesian statistics. However, evaluating the likelihood of an observation is computationally intractable in many applications. In this paper, we propose a non-parametric approximation of the likelihood ...
2019
Online services are becoming more and more ubiquitous and keep growing in scale. At the same time, they are required to be highly available, secure, energy-efficient, and to achieve high performance. To ensure these (and many other) properties, replication ...
EPFL2019
Blockchains have captured the attention of many, resulting in an abundance of new systems available for use. However, selecting an appropriate blockchain for an application is challenging due to the lack of comparative information discussing core metrics s ...
IEEE2020
, , , ,
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 bugs, c ...
2018
Studying the complexity of distributed algorithms typically boils down to evaluating how the number of messages exchanged (resp. communication steps performed or shared memory operations executed) by nodes to reliably achieve some common task, evolves with ...
Wasserstein distances are metrics on probability distributions inspired by the problem of optimal mass transportation. Roughly speaking, they measure the minimal effort required to reconfigure the probability mass of one distribution in order to recover th ...
The growth and establishment of riparian vegetation on river bedforms is of hydrological as well as ecological importance as it helps in enhancing spatial heterogeneity and thus the biodiversity of river corridors. Yet, during floods, flow drag and scourin ...
The problem of control synthesis to maximize the probability of satisfying automata specifications for systems with uncertainty is addressed. Two types of uncertainty are considered; stochasticity in the dynamical system and in the sets defining the specif ...