Out-of-distribution extrapolation is non-identifiable from in-distribution data alone; the feature map, label map, and model class supply the identifiability bias that determines whether a network succeeds or fails at OOD generalization.
6.3).(a)schematic ( Pvis=6): random input xt, periodic target yt =f(tmodP) ; OOD continues the same pattern past Ltrain.(b)full scale ( P=64 )
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
-
Does Your Neural Network Extrapolate? Feature Engineering as Identifiability Bias for OOD Generalization
Out-of-distribution extrapolation is non-identifiable from in-distribution data alone; the feature map, label map, and model class supply the identifiability bias that determines whether a network succeeds or fails at OOD generalization.