FRM replaces output-space losses with function-space losses, fitting a per-data-point function and approximating the resulting objective with Taylor/Laplace expansions, yielding weighted least squares with a Jacobian-Hessian metric.
Spatial transformer networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Functional Risk Minimization
FRM replaces output-space losses with function-space losses, fitting a per-data-point function and approximating the resulting objective with Taylor/Laplace expansions, yielding weighted least squares with a Jacobian-Hessian metric.