Introduces transitive inference with exceptions task and analytically shows kernel ridge regression balances relational generalization and memorization depending on representational geometry, with validation in finetuned language models.
Gradient descent follows the regularization path for general losses
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
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.
citing papers explorer
-
A mathematical theory of balancing relational generalization and memorization
Introduces transitive inference with exceptions task and analytically shows kernel ridge regression balances relational generalization and memorization depending on representational geometry, with validation in finetuned language models.
-
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.