UFO: Uncertainty Feature Optimization, an Implicit Paradigm for Problems with Noisy Data

In this work, we present a new framework to cope with problems due to uncertainty. We consider the uncertainty implicitly with helps of Uncertainty Feature Optimization (UFO), i.e. we transform the initial problem to a multi-objective problem. The aim is to increase structural properties of a solution that are known to improve it's robustness or it's recoverability