Derives generalization bounds for perturbed surrogate policies in combinatorial optimization by decomposing excess risk into perturbation bias controlled by fan-crossing probability, statistical estimation error, and optimization error.
A pac approach to applicati on-specific algorithm selection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Generalization Bounds of Surrogate Policies for Combinatorial Optimization Problems
Derives generalization bounds for perturbed surrogate policies in combinatorial optimization by decomposing excess risk into perturbation bias controlled by fan-crossing probability, statistical estimation error, and optimization error.