Regularized kernel logistic classifiers decompose into an ideal template classifier plus a perturbation from token overlaps modeled by a colored collision graph, yielding high-probability margin-transfer guarantees for fresh-symbol classification.
InProceedings of the 35th International Conference on Machine Learning, Proceedings of Machine Learning Research, volume 80, pages 2873–2882, PMLR
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
-
When Symbol Names Should Not Matter: A Logistic Theory of Fresh-Symbol Classification
Regularized kernel logistic classifiers decompose into an ideal template classifier plus a perturbation from token overlaps modeled by a colored collision graph, yielding high-probability margin-transfer guarantees for fresh-symbol classification.