New conditions for support vector proliferation (SVP) in RKHS for bounded orthonormal systems and sub-Gaussian features, yielding generalization bounds for kernel SVMs beyond prior restrictive assumptions.
Two models of double descen t for weak features
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Repetition of training data produces a systematic eval loss peak at intermediate repeat counts whose location scales with model size, quantifiable as large compute-equivalent loss even at modest repetition fractions.
citing papers explorer
-
New Equivalences Between Interpolation and SVMs: Kernels and Structured Features
New conditions for support vector proliferation (SVP) in RKHS for bounded orthonormal systems and sub-Gaussian features, yielding generalization bounds for kernel SVMs beyond prior restrictive assumptions.