On the Safety of Machine Learning: Cyber-Physical Systems, Decision Sciences, and Data Products

Machine learning algorithms are increasingly influencing our decisions and interacting with us in all parts of our daily lives. Therefore, just like for power plants, highways, and a myriad of other engineered socio-technical systems, we must consider the safety of systems involving machine learning. Heretofore, the definition of safety has not been formalized in the machine learning context; in this paper, we do so by defining machine learning safety in terms of risk, epistemic uncertainty, and the harm incurred by unwanted outcomes. We then use this definition to examine safety in all sorts of applications in cyberphysical systems, decision sciences and data products, finding that the foundational principle of modern statistical machine learning, empirical risk minimization, is not always a sufficient objective. In particular, we note an emerging dichotomy of applications: ones in which safety is important and risk minimization is not the complete story (we name these Type A applications), and ones in which safety is not so critical and risk minimization is sufficient (we name these Type B applications). Finally, we discuss how four different strategies for achieving safety in engineering (inherently safe design, safety reserves, safe fail, and procedural safeguards) can be mapped to the machine learning context through interpretability and causality of predictive models, objectives beyond expected prediction accuracy, human involvement for labeling difficult or rare examples, and user experience design of software and open data.