Fault-tolerant federated reinforcement learning with theoretical guarantee
The growing literature of Federated Learning (FL) has recently inspired Federated
Reinforcement Learning (FRL) to encourage multiple agents to federatively build a better …
Reinforcement Learning (FRL) to encourage multiple agents to federatively build a better …
Byzantine-resilient decentralized stochastic optimization with robust aggregation rules
This article focuses on decentralized stochastic optimization in the presence of Byzantine
attacks. During the optimization process, an unknown number of malfunctioning or malicious …
attacks. During the optimization process, an unknown number of malfunctioning or malicious …
Byzantine-robust distributed online learning: Taming adversarial participants in an adversarial environment
This paper studies distributed online learning under Byzantine attacks. The performance of
an online learning algorithm is often characterized by (adversarial) regret, which evaluates …
an online learning algorithm is often characterized by (adversarial) regret, which evaluates …
Byzantine-robust variance-reduced federated learning over distributed non-iid data
We consider the federated learning problem where data on workers are not independent
and identically distributed (iid). During the learning process, an unknown number of …
and identically distributed (iid). During the learning process, an unknown number of …
Broadcast: Reducing both stochastic and compression noise to robustify communication-efficient federated learning
Communication between workers and the master node to collect local stochastic gradients is
a key bottleneck in a large-scale federated learning system. Various recent works have …
a key bottleneck in a large-scale federated learning system. Various recent works have …
Byzantine-robust distributed learning with compression
Communication between workers and the master node to collect local stochastic gradients is
a key bottleneck in a large-scale distributed learning system. Various recent works have …
a key bottleneck in a large-scale distributed learning system. Various recent works have …
Variance reduction-boosted Byzantine robustness in decentralized stochastic optimization
We consider the Byzantine-robust decentralized stochastic optimization problem, where
every agent periodically communicates with its neighbors to exchange the local models, and …
every agent periodically communicates with its neighbors to exchange the local models, and …
Byzantine-robust decentralized stochastic optimization with stochastic gradient noise-independent learning error
This paper studies Byzantine-robust stochastic optimization over a decentralized network,
where every agent periodically communicates with its neighbors to exchange local models …
where every agent periodically communicates with its neighbors to exchange local models …
Distributed online learning with adversarial participants in an adversarial environment
This paper studies distributed online learning under Byzantine attacks. The performance of
an online learning algorithm is characterized by (adversarial) regret, and a sublinear bound …
an online learning algorithm is characterized by (adversarial) regret, and a sublinear bound …
Byzantine-robust decentralized stochastic optimization with stochastic gradient noise-independent learning error
This paper studies Byzantine-robust stochastic optimization over a decentralized network,
where every agent periodically communicates with its neighbors to exchange local models …
where every agent periodically communicates with its neighbors to exchange local models …