no code implementations • 24 May 2024 • Haoze He, Juncheng Billy Li, Xuan Jiang, Heather Miller
In this work, we introduce a method for selecting sparse sub-matrices that aim to minimize the performance gap between PEFT vs. full fine-tuning (FT) while also reducing both fine-tuning computational cost and memory cost.
no code implementations • 18 May 2024 • Haoze He, Jing Wang, Anna Choromanska
This work focuses on the decentralized deep learning optimization framework.
no code implementations • 2 Nov 2022 • Haoze He, Parijat Dube
In this paper, we propose the (de)centralized Non-blocking SGD (Non-blocking SGD) which can address the straggler problem in a heterogeneous environment.
no code implementations • 2 Nov 2022 • Haoze He, Parijat Dube
The convergence of SGD based distributed training algorithms is tied to the data distribution across workers.