SEDGE provides conditions and algorithms for reliably generating extrapolated data outside the training distribution under structural assumptions on the data-generating process.
org/CorpusID:232035663
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
-
SEDGE: Structural Extrapolated Data Generation
SEDGE provides conditions and algorithms for reliably generating extrapolated data outside the training distribution under structural assumptions on the data-generating process.