Zobrazeno 1 - 10
of 229
pro vyhledávání: '"Stephan, John"'
Batch normalization has proven to be a very beneficial mechanism to accelerate the training and improve the accuracy of deep neural networks in centralized environments. Yet, the scheme faces significant challenges in federated learning, especially u
Externí odkaz:
http://arxiv.org/abs/2405.14670
Autor:
Allouah, Youssef, Guerraoui, Rachid, Gupta, Nirupam, Jellouli, Ahmed, Rizk, Geovani, Stephan, John
Robust distributed learning consists in achieving good learning performance despite the presence of misbehaving workers. State-of-the-art (SOTA) robust distributed gradient descent (Robust-DGD) methods, relying on robust aggregation, have been proven
Externí odkaz:
http://arxiv.org/abs/2405.14432
The success of machine learning (ML) applications relies on vast datasets and distributed architectures which, as they grow, present major challenges. In real-world scenarios, where data often contains sensitive information, issues like data poisonin
Externí odkaz:
http://arxiv.org/abs/2312.14712
Autor:
Choffrut, Antoine, Guerraoui, Rachid, Pinot, Rafael, Sirdey, Renaud, Stephan, John, Zuber, Martin
Due to the widespread availability of data, machine learning (ML) algorithms are increasingly being implemented in distributed topologies, wherein various nodes collaborate to train ML models via the coordination of a central server. However, distrib
Externí odkaz:
http://arxiv.org/abs/2309.05395
The ubiquity of distributed machine learning (ML) in sensitive public domain applications calls for algorithms that protect data privacy, while being robust to faults and adversarial behaviors. Although privacy and robustness have been extensively st
Externí odkaz:
http://arxiv.org/abs/2302.04787
Autor:
Allouah, Youssef, Farhadkhani, Sadegh, Guerraoui, Rachid, Gupta, Nirupam, Pinot, Rafael, Stephan, John
Byzantine machine learning (ML) aims to ensure the resilience of distributed learning algorithms to misbehaving (or Byzantine) machines. Although this problem received significant attention, prior works often assume the data held by the machines to b
Externí odkaz:
http://arxiv.org/abs/2302.01772
Autor:
El-Mhamdi, El-Mahdi, Farhadkhani, Sadegh, Guerraoui, Rachid, Gupta, Nirupam, Hoang, Lê-Nguyên, Pinot, Rafael, Rouault, Sébastien, Stephan, John
Large AI Models (LAIMs), of which large language models are the most prominent recent example, showcase some impressive performance. However they have been empirically found to pose serious security issues. This paper systematizes our knowledge about
Externí odkaz:
http://arxiv.org/abs/2209.15259
Autor:
Farhadkhani, Sadegh, Guerraoui, Rachid, Gupta, Nirupam, Hoang, Lê Nguyên, Pinot, Rafael, Stephan, John
Collaborative learning algorithms, such as distributed SGD (or D-SGD), are prone to faulty machines that may deviate from their prescribed algorithm because of software or hardware bugs, poisoned data or malicious behaviors. While many solutions have
Externí odkaz:
http://arxiv.org/abs/2209.10931
Byzantine resilience emerged as a prominent topic within the distributed machine learning community. Essentially, the goal is to enhance distributed optimization algorithms, such as distributed SGD, in a way that guarantees convergence despite the pr
Externí odkaz:
http://arxiv.org/abs/2205.12173
Privacy and Byzantine resilience (BR) are two crucial requirements of modern-day distributed machine learning. The two concepts have been extensively studied individually but the question of how to combine them effectively remains unanswered. This pa
Externí odkaz:
http://arxiv.org/abs/2110.03991