Bilinear Optimization Divergence: Diagnosing Factor-Constrained LoRA Continual Learning
The analysis and evidence provide an architecture-conditioned account of which constraint to enforce, how to enforce it, and how to interpret its empirical value, and show that stricter feasibility need not improve final task performance.
Yong-Shun Wang, Jianlin Su, Yong-Yi Ma
· 1 citation