Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Beyond LoRA: Is Sparsity-Induced Adaptation Better?
Elijah Cadenhead, Cristian McGee, Xin Li +2
Low-rank adaptation (LoRA) and its variants provide a memory- and compute-efficient alternative to full fine-tuning of pre-trained models. However, questions remain about the compa…
cs.LG2025
Kolmogorov-Arnold Attention: Is Learnable Attention Better For Vision Transformers?
Subhajit Maity, Killian Hitsman, Xin Li +1
Kolmogorov-Arnold networks (KANs) are a remarkable innovation that consists of learnable activation functions, with the potential to capture more complex relationships from data. P…
cs.LG2023
Demystifying the Myths and Legends of Nonconvex Convergence of SGD
Aritra Dutta, El Houcine Bergou, Soumia Boucherouite +3
Stochastic gradient descent (SGD) and its variants are the main workhorses for solving large-scale optimization problems with nonconvex objective functions. Although the convergenc…