34 citations · 59 across the 3 of their papers we have counts for
3 papers
Virtuously Safe Reinforcement Learning
Henrik Aslund, El Mahdi El Mhamdi, Rachid Guerraoui +1
We show that when a third party, the adversary, steps into the two-party setting (agent and operator) of safely interruptible reinforcement learning, a trade-off has to be made bet…
When Neurons Fail
El Mahdi El Mhamdi, Rachid Guerraoui
We view a neural network as a distributed system of which neurons can fail independently, and we evaluate its robustness in the absence of any (recovery) learning phase. We give ti…
Byzantine-Tolerant Machine Learning
Peva Blanchard, El Mahdi El Mhamdi, Rachid Guerraoui +1
The growth of data, the need for scalability and the complexity of models used in modern machine learning calls for distributed implementations. Yet, as of today, distributed machi…