#近似理论

1 stories · 0 in 7 days · 0 in 30 days

Stories, products and papers tagged "近似理论", newest first.

Aug 27

PapersSelected10:29

LoRA Rank Error Bounds for Transformer Attention

The theoretical bounds help practitioners choose optimal LoRA ranks for efficient Transformer fine-tuning, reducing computational costs while maintaining performance.

#LoRA #Transformer attention #KL error #low-rank adaptation

arXiv cs.AI@Gerard Conangla PlanesSource