AI RESEARCH
On the Koopman-Based Generalization Bounds for Multi-Task Deep Learning
arXiv CS.AI
•
ArXi:2512.19199v2 Announce Type: replace-cross The paper establishes generalization bounds for multitask deep neural networks using operator-theoretic techniques. The authors propose a tighter bound than those derived from conventional norm based methods by leveraging small condition numbers in the weight matrices and