#artificial intelligence
Jan 2026
Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models
This work reformulates the deterministic LoRA update as a probabilistic low-rank representation inspired by Sparse Gaussian Processes, and identifies a structural isomorphism between LoRA's factorization and Kronecker-factored SGP posteriors, and shows that LoRA emerges as a limiting case when posterior uncertainty col...
Mou-Le Lin, Shu-Hao Guan, Andrea Patane et al.
· arXiv.org · 1 citation