Upper Bounds on the Expected Value of a Convex Function Using Gradient and Conjugate Function Information
Published Online:1 Nov 1989https://doi.org/10.1287/moor.14.4.745
Abstract
New upper bounds are given for the expected value of a convex function. The bounds employ subgradient information and the conjugate function. In contrast to most other bounds, explicit moment information is not needed. We derive the bounds and compare them with previous bounds with different information requirements.
