Engineering Trustworthy AI: A Developer Guide for Empirical Risk Minimization
This addresses the need for developers to build AI systems that meet emerging trustworthiness standards, though it is incremental as it adapts existing ERM methods.
The paper tackles the problem of AI systems prioritizing accuracy over trustworthiness in empirical risk minimization (ERM), leading to biases and opacity, by providing actionable guidance to translate trustworthiness requirements into ERM design choices.
AI systems increasingly shape critical decisions across personal and societal domains. While empirical risk minimization (ERM) drives much of the AI success, it typically prioritizes accuracy over trustworthiness, often resulting in biases, opacity, and other adverse effects. This paper discusses how key requirements for trustworthy AI can be translated into design choices for the components of ERM. We hope to provide actionable guidance for building AI systems that meet emerging standards for trustworthiness of AI.