4 papers · 1 filter
SageBwd: A Trainable Low-bit Attention
Jintao Zhang, Marco Chen, Haoxu Wang +5
Low-bit attention, such as SageAttention, has emerged as an effective approach for accelerating model inference, but its applicability to training remains poorly understood. In pri…
Delving into Muon and Beyond: Deep Analysis and Extensions
Xianbiao Qi, Marco Chen, Jiaquan Ye +2
The Muon optimizer has recently attracted considerable attention for its strong empirical performance and use of orthogonalized updates on matrix-shaped parameters, yet its underly…
SimpleGPT: Improving GPT via A Simple Normalization Strategy
Marco Chen, Xianbiao Qi, Yelin He +2
In this work, we revisit Transformer optimization through the lens of second-order geometry and establish a direct connection between architectural design, activation scale, the He…
DNT: a Deeply Normalized Transformer that can be trained by Momentum SGD
Xianbiao Qi, Marco Chen, Wenjie Xiao +4
Transformers have become the de facto backbone of modern deep learning, yet their training typically demands an advanced optimizer with adaptive learning rate like AdamW, rather th…