Norm-Bounded Low-Rank Adaptation

원문 초록

In this work, we propose norm-bounded low-rank adaptation (NB-LoRA) for parameter-efficient fine tuning. We introduce two parameterizations that allow explicit bounds on each singular value of the weight adaptation matrix, which can therefore satisfy any prescribed unitarily invariant norm bound, including the Schatten norms (e.g., nuclear, Frobenius, spectral norm). The proposed parameterizations are unconstrained and complete, i.e. they cover all matrices satisfying the prescribed rank and norm constraints. Experiments on vision fine-tuning benchmarks show that the proposed approach can achieve good adaptation performance while avoiding model catastrophic forgetting and also substantially improve robustness to a wide range of hyper-parameters, including adaptation rank, learning rate and number of training epochs. We also explore applications in privacy-preserving model merging and low-rank matrix completion.