Branch Scaling Manifests as Implicit Architectural Regularization for Improving Generalization in Overparameterized ResNets

ArXi:2403.04545v2 Announce Type: replace Scaling factors in residual branches have emerged as a prevalent method for boosting neural network performance, especially in normalization-free architectures. While prior work has primarily examined scaling effects from an optimization perspective, this paper investigates their role in residual architectures through the lens of generalization theory. Specifically, we establish that wide residual networks (ResNets) with constant scaling factors become asymptotically unlearnable as depth increases.