Positive simplex weights for kernel quadrature achieve O(d/N) convex-hull approximation error in feature space, transferring to RKHS worst-case bounds that beat Monte Carlo under exponential spectral decay.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.NA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Convex-Geometric Error Bounds for Positive-Weight Kernel Quadrature
Positive simplex weights for kernel quadrature achieve O(d/N) convex-hull approximation error in feature space, transferring to RKHS worst-case bounds that beat Monte Carlo under exponential spectral decay.