Neural networks cannot approximate matrix inversion over domains approaching singular matrices; in safe regions they merely learn the local linear Taylor approximation of the inverse.
Sorting out lipschitz function approximation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Rethinking Neural-based Matrix Inversion: Why can't, and Where can
Neural networks cannot approximate matrix inversion over domains approaching singular matrices; in safe regions they merely learn the local linear Taylor approximation of the inverse.