Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
SCPL: Enhancing Neural Network Training Throughput with Decoupled Local Losses and Model Parallelism
Ming-Yao Ho, Cheng-Kai Wang, You-Teng Lin +1
Adopting large-scale AI models in enterprise information systems is often hindered by high training costs and long development cycles, posing a significant managerial challenge. Th…
cs.LG2025
DeInfoReg: A Decoupled Learning Framework for Better Training Throughput
Zih-Hao Huang, You-Teng Lin, Hung-Hsuan Chen
This paper introduces Decoupled Supervised Learning with Information Regularization (DeInfoReg), a novel approach that transforms a long gradient flow into multiple shorter ones, t…