From Data to Decisions: Distributionally Robust Optimization Is Optimal 3: On a Compact Continuous State Space the Relative-Entropy Robust Predictor Is Feasible and Strongly OptimalResearch Paper
A decision maker who chooses to minimize an expected cost rarely knows the distribution of the random parameter . What is available is a sample . Any rule that turns the sample into a cost estimate can disappoint: the realized expected cost may exceed the estimate. In a…