GitHub / fzhu0628 1 Repository
PhD student @North Carolina State University | B.E. & M.E. from Fudan University | Working on Optimization, Federated Learning, and Theoretical (Multi-Agent) RL
fzhu0628/FedHSA---Tighter-Rates-for-Heterogeneous-Federated-Stochastic-Approximation-under-Markovian-Sampling
This is the second paper of my PhD career. Focusing on the general stochastic approximation framework, it proposes a federated algorithm that finds the optimum of an average of contractive operators.
Language: Python - Size: 25.4 KB - Last synced at: 23 days ago - Pushed at: 23 days ago - Stars: 0 - Forks: 0
fzhu0628/Fast-FedPG---Towards-Fast-Rates-for-Federated-and-Multi-Task-Reinforcement-Learning
This work is a conference paper published at IEEE CDC 2024. The paper is dedicated to finding a policy that maximizes the average of long-term cumulative rewards across environments. Included in the repository are a brief introduction of our work, the poster for the AI Symposium at NCSU, and the slides for the CDC talk.
Size: 2.19 MB - Last synced at: 6 months ago - Pushed at: 6 months ago - Stars: 0 - Forks: 0
fzhu0628/fzhu0628
Config files for my GitHub profile.
Size: 3.91 KB - Last synced at: 6 months ago - Pushed at: 6 months ago - Stars: 0 - Forks: 0
fzhu0628/DRAG-Divergence-Based-Adaptive-Aggregation-in-Federated-Learning-on-Non-IID-Data
In this work, we developed a novel algorithm named divergence-based adaptive aggregation (DRAG) to deal with the client-drift effect. Additionally, the DRAG algorithm also showcases resilience against byzantine attacks, as demonstrated through experiments.
Size: 0 Bytes - Last synced at: 7 months ago - Pushed at: 7 months ago - Stars: 0 - Forks: 0
fzhu0628/STSyn---Speeding-up-local-SGD-with-straggler-tolerant-synchronization
This work is a journal paper published at IEEE TSP in 2024, concentrating on improving the robustness to stragglers in distributed/federated learning with synchronous local SGD.
Size: 3.91 KB - Last synced at: 7 months ago - Pushed at: 7 months ago - Stars: 0 - Forks: 0
fzhu0628/G-CADA---Adaptive-worker-grouping-for-communication-efficient-and-straggler-tolerant-distributed-SGD
This work was published at IEEE ISIT 2022, where we proposed a novel algorithm named G-CADA aiming to improve the time and communication efficiency of distributed learning systems based on grouping and adaptive selection methods :smile:
Language: Python - Size: 11.7 KB - Last synced at: 7 months ago - Pushed at: 7 months ago - Stars: 0 - Forks: 0
fzhu0628/AgeSel---Communication-efficient-local-SGD-with-age-based-worker-selection
This work is a journal paper published at The Journal of Supercomputing in 2023, focusing on improving communication efficiency of a distributed learning system using age-based worker selection techniques.
Language: Python - Size: 1.95 KB - Last synced at: 7 months ago - Pushed at: 7 months ago - Stars: 0 - Forks: 0