After training, a 110M-parameter power-law attention model's learned scoring operator becomes nearly input-invariant, so inference can cache it; the paper proves this collapse conditionally, measures it at 1e-6 and below, and machine-checks selected proofs in Lean 4.
Muñoz, Alessandro Vespignani, and Stefano Zapperi,Paths to self-organized criticality, Brazilian Journal of Physics30(2000), no
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
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference
After training, a 110M-parameter power-law attention model's learned scoring operator becomes nearly input-invariant, so inference can cache it; the paper proves this collapse conditionally, measures it at 1e-6 and below, and machine-checks selected proofs in Lean 4.