no code implementations • 26 Jul 2023 • Behzad Nourani-Koliji, Steven Bilaj, Amir Rezaei Balef, Setareh Maghsudi
In our nonstationary environment, variations in the base arms' distributions, causal relationships between rewards, or both, change the reward generation process.
1 code implementation • 10 Feb 2023 • Amir Rezaei Balef, Setareh Maghsudi
Without this assumption, the regret bound of our algorithm is $\gamma_T\log(T)$.
2 code implementations • 10 Dec 2020 • Canh T. Dinh, Nguyen H. Tran, Tuan Dung Nguyen, Wei Bao, Amir Rezaei Balef, Bing B. Zhou, Albert Y. Zomaya
In this work, we propose DONE, a distributed approximate Newton-type algorithm with fast convergence rate for communication-efficient federated edge learning.