The limitations of optimization from samples
Eric Balkanski, Aviad Rubinstein, Yaron Singer · 2017
In this paper we consider the following question: can we optimize objective functions from the training data we use to learn them? We formalize this question through a novel framework we call optimization from samples (OPS). In OPS, we are given sampled values of a function drawn from some distribution and the objective is to optimize the function under some constraint.