SignSGD: Fault-Tolerance to Blind and Byzantine Adversaries

Distributed learning has become a necessity for training ever-growing models. In a distributed setting, the task is shared among several devices. Typically, the learning process is monitored by a server. Also, some of the devices can be faulty, deliberately or not, and the usual distributed SGD algorithm cannot defend itself from omniscient adversaries. Therefore, we need to devise a fault-tolerant gradient descent algorithm. We based our article on the SignSGD algorithm, which relies on the sharing of gradients signs between the devices and the server. We provide a theoretical upper bound for the convergence rate of SignSGD to extend the results of the original paper. Our theoretical results estimate the convergence rate of SignSGD against a proportion of general adversaries, such as Byzantine adversaries. We implemented the algorithm along with Byzantine strategies in order to try to crush the learning process. Therefore, we provide empirical observations from our experiments to support our theory. Our code is available on GitHub and our experiments are reproducible by using the provided parameters.