Upper Bounds on the Expected Value of a Convex Function Using Gradient and Conjugate Function Information.
Abstract
New upper bounds are given for the expected value of a convex function. The bounds employ subgradient information and the conjugate function. The bounds are derived and compared with previous bounds with different information requirements. Keywords: Bounds; Convex functions; Stochastic programs; Utility functions.
Document Details
- Document Type
- Technical Report
- Publication Date
- Aug 01, 1987
- Accession Number
- ADA186246
Entities
People
- John R. Birge
- Marck Teboulle
Organizations
- University of Michigan