Proves NP-hardness of computing decision-relevant dimension d* and coNP-hardness of global sufficiency in linear optimization, then gives poly-time pointwise algorithms, a cumulative compression scheme of size at most d*, and PAC bounds scaling with d* for contextual linear optimization.
How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design.Journal of the ACM, 71(5):32:1–32:58, 2024a
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning Decision-Sufficient Representations for Linear Optimization
Proves NP-hardness of computing decision-relevant dimension d* and coNP-hardness of global sufficiency in linear optimization, then gives poly-time pointwise algorithms, a cumulative compression scheme of size at most d*, and PAC bounds scaling with d* for contextual linear optimization.