This work incorporates an additive structure into the DG framework and employs ℓq,1 -norm regularization to induce sparsity, thereby enabling structured feature selection and enhancing interpretability and presents two distinct realizations: an additive kernel-based formulation and a neural additive model-based approac...
Jia-Yi Wang, Han Li· Proceedings of the 32nd ACM...· 0 citations
Machine learning models continue to face challenges in out-of-distribution (OOD) generalization, where domain generalization (DG) aims to improve performance on unseen domains under distributional shifts. A prevalent paradigm in DG focuses on learning domain-invariant feature representations. However, feature represent...
Jiayi Wang, Han Li· Proceedings of the 32nd ACM...· 0 citations
This work establishes a high-probability generalization bound for ViTs in classification tasks under adversarial settings, and elucidates the roles of several factors in mitigating perturbation effects, norm regularization of weight matrices and depth-wise propagation constraints on layer-wise norms.
Zi-Wen Jiang, Chang Cao, Han Li et al.· Proceedings of the Thirty-Fi...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
