15 citations · 47 across the 20 of their papers we have counts for
7 papers · 1 filter
High-probability zeroth-order online convex optimisation beyond Euclidean geometry
David Janz, El-Mahdi El-Mhamdi, Arya Akhavan
We study online convex optimisation with -Lipschitz losses, -regularised FTRL, and randomised two-point finite-difference gradient estimators based on cone-measure…
On the Byzantine Fault Tolerance of signSGD with Majority Vote
Emanuele Mengoli, Luzius Moll, Virgilio Strozzi +1
In distributed learning, sign-based compression algorithms such as signSGD with majority vote provide a lightweight alternative to SGD with an additional advantage: fault tolerance…
Inverting Gradient Attacks Makes Powerful Data Poisoning
Wassim Bouaziz, El-Mahdi El-Mhamdi, Nicolas Usunier
Gradient attacks and data poisoning tamper with the training of machine learning algorithms to maliciously alter them and have been proven to be equivalent in convex settings. The…
On the Impossible Safety of Large AI Models
El-Mahdi El-Mhamdi, Sadegh Farhadkhani, Rachid Guerraoui +5
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 pos…
Garfield: System Support for Byzantine Machine Learning
Rachid Guerraoui, Arsany Guirguis, Jérémy Max Plassmann +2
We present Garfield, a library to transparently make machine learning (ML) applications, initially built with popular (but fragile) frameworks, e.g., TensorFlow and PyTorch, Byzant…
Collaborative Learning in the Jungle (Decentralized, Byzantine, Heterogeneous, Asynchronous and Nonconvex Learning)
El-Mahdi El-Mhamdi, Sadegh Farhadkhani, Rachid Guerraoui +3
We study Byzantine collaborative learning, where nodes seek to collectively learn from each others' local data. The data distribution may vary from one node to another. No node…
Distributed Momentum for Byzantine-resilient Learning
El-Mahdi El-Mhamdi, Rachid Guerraoui, Sébastien Rouault
Momentum is a variant of gradient descent that has been proposed for its benefits on convergence. In a distributed setting, momentum can be implemented either at the server or the…