A nonlinear adjoint operator rewrites nonlinear least-squares losses as norms of a data-dependent matrix, enabling leverage-score and row-norm sampling with subspace-embedding-style guarantees.
Random fourier features for kernel ridge regression: Approximation bounds and statistical guarantees
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Importance Sampling for Nonlinear Models
A nonlinear adjoint operator rewrites nonlinear least-squares losses as norms of a data-dependent matrix, enabling leverage-score and row-norm sampling with subspace-embedding-style guarantees.