Tighter Learning Guarantees on Digital Computers via Concentration of Measure on Finite Spaces
arXiv:2402.05576v4 Announce Type: replace
Abstract: Machine learning models with inputs in a Euclidean space $\mathbb{R}^d$, when implemented on digital computers, generalize, and their generalization gap converges to $0$ at a rate of $c/N^{1/2}$ conc…