Sparse gradient communication for accelerating distributed deep learning
Zihan Li · 2024
HKUST Electronic Theses Sparse gradient communication for accelerating distributed deep learning by Li Zihan thesis 2024 1 online resource (ix, 40 pages) : illustrations (chiefly color) Synchronous stochastic gradient descent (S-SGD) with data parallelism has become a de-facto approach in…Read more ›