Shiyun Xu

Convex Dominance in Deep Learning I: A Scaling Law of Loss and Learning Rate

FlowNIB: An Information Bottleneck Analysis of Bidirectional vs. Unidirectional Language Models

Adaptive parameter-efficient fine-tuning via multi-task optimization on subset selection

Gradient descent with generalized Newton’s method

Not all parameters are equal: a Hessian informed differential learning rate for deep learning