SchoenbAt approximates dot-product kernelized attention with random Maclaurin features under Schoenberg's theorem, adding a batch-normalization step that keeps inputs within the theorem's domain.
Learning to weight samples for dynamic early-exiting networks
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
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
SchoenbAt: Rethinking Attention with Polynomial basis
SchoenbAt approximates dot-product kernelized attention with random Maclaurin features under Schoenberg's theorem, adding a batch-normalization step that keeps inputs within the theorem's domain.