DReS: Dual Reconstruction Smoothing for Functional Regularization

ArXi:2510.00253v2 Announce Type: replace Smoothness is a key inductive bias in machine learning and is closely related to generalization. Existing smoothness-inducing methods typically rely either on explicit gradient regularization, which often incurs substantial computational and memory overhead, or on data-mixing strategies, which are less naturally applicable to unsupervised and self-supervised settings.