A doubly-randomized feature map for Bernstein-Schur kernels achieves unbiased kernel approximation with variance and operator-norm bounds controlled by effective dimension rather than crude maxima.
arXiv preprint arXiv:2110.06081 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Bernstein-Schur Kernels: Random Features by Sketched Modulation and Radial Randomization
A doubly-randomized feature map for Bernstein-Schur kernels achieves unbiased kernel approximation with variance and operator-norm bounds controlled by effective dimension rather than crude maxima.