all AI news
Koopman-based generalization bound: New aspect for full-rank weights
March 19, 2024, 4:44 a.m. | Yuka Hashimoto, Sho Sonoda, Isao Ishikawa, Atsushi Nitanda, Taiji Suzuki
cs.LG updates on arXiv.org arxiv.org
Abstract: We propose a new bound for generalization of neural networks using Koopman operators. Whereas most of existing works focus on low-rank weight matrices, we focus on full-rank weight matrices. Our bound is tighter than existing norm-based bounds when the condition numbers of weight matrices are small. Especially, it is completely independent of the width of the network if the weight matrices are orthogonal. Our bound does not contradict to the existing bounds but is a …
abstract arxiv cs.lg focus low math.fa networks neural networks norm numbers operators small stat.ml type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Robotics Technician - 3rd Shift
@ GXO Logistics | Perris, CA, US, 92571