7 citations · 7 across the 5 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
A Riemannian Geometry for Low-rank Adaptation
Shoichiro Takeda, Shin'ya Yamaguchi, Satoshi Suzuki +1
Low-rank adaptation (LoRA) is widely used as a parameter-efficient fine-tuning technique for pre-trained deep neural networks, which approximates the weight update via full fine-tu…
cs.LG2023
Optimal Transport with Cyclic Symmetry
Shoichiro Takeda, Yasunori Akagi, Naoki Marumo +1
We propose novel fast algorithms for optimal transport (OT) utilizing a cyclic symmetry structure of input data. Such OT with cyclic symmetry appears universally in various real-wo…