Learning to cut requires at least as many samples as learning any generic target from the same concept class, for both gap closed and branch-and-cut tree size scores.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
How hard is learning to cut? Trade-offs and sample complexity
Learning to cut requires at least as many samples as learning any generic target from the same concept class, for both gap closed and branch-and-cut tree size scores.