Derives tighter Koopman-based generalization bounds for multi-task DNNs by assuming small weight-matrix condition numbers and using a tailored Sobolev space as hypothesis class.
In: Proceedings of the 39th International Conference on Machine Learning (ICML) (2022)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
On the Koopman-Based Generalization Bounds for Multi-Task Deep Learning
Derives tighter Koopman-based generalization bounds for multi-task DNNs by assuming small weight-matrix condition numbers and using a tailored Sobolev space as hypothesis class.