RiskBoundsandCalibrationforaSmart Predict-then-OptimizeMethod

Neural Information Processing Systems 

Moreover, since the SPO loss is not continuous nor convex in general [Elmachtoub and Grigas, 2021], which makesthe training ofaprediction model computationally intractable, Elmachtoub and Grigas [2021] introduced a novel convex surrogate loss, referred to as the SPO+ loss.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found