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.
Mechanisms of Symbol Processing for In-Context Learning in Transformer Networks.Journal of Artificial Intelligence Research, 84(23)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 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.