← Search

Jui-Nan Yen

2 accepted papers

2025

LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization

ICLR 2025oral

Low-rank adaption (LoRA) is a widely used parameter-efficient finetuning method for LLM that reduces memory requirements. However, current LoRA optimizers lack transformation invariance, meaning the updates depending on how the two LoRA factors are scaled or rotated. This deficiency leads to ineffic…

2023

Block Low-Rank Preconditioner with Shared Basis for Stochastic Optimization

NeurIPS 2023poster

Adaptive methods with non-diagonal preconditioning have shown state-of-the-art results on various tasks. However, their computational complexity and memory requirement makes it challenging to scale these methods to modern neural network architectures. To address this challenge, some previous works h…

Cited by 4SourcePDFScholar