2 papers
cs.LG2026
Subspace Networks: Scaling Decentralized Training with Communication-Efficient Model Parallelism
Sameera Ramasinghe, Thalaiyasingam Ajanthan, Gil Avraham +2
Scaling models has led to significant advancements in deep learning, but training these models in decentralized settings remains challenging due to communication bottlenecks. While…
cs.LG2026
Taming Curvature: Architecture Warm-Up for Stable Transformer Training
Sameera Ramasinghe, Ajanthan Thalaiyasingam, Hadi Mohaghegh Dolatabadi +6
Training billion-parameter Transformers is often brittle, with transient loss spikes and divergence that waste compute. Even though the recently developed Edge of Stability (EoS) t…