arXiv stat.ML
· Papers
Fisher Widths: Local Learning Geometry and Anisotropic Recovery
arXiv:2607.20578v1 Announce Type: cross Abstract: We study Gaussian-width complexity on statistical manifolds through a pair of functionals: the primal Fisher width $w_G(T) = w(G^{1/2}T)$, induced by the Fisher metric, and the inverse-Fisher width $w_{G^{-1}}(T) = w(G^{-1/2}T)$, induced by the inverse Fisher metric. Th