The Cambridge ELLIS Unit Seminar Series holds talks by leading researchers in the area of machine learning and AI. Our first speaker of 2023 will be Dr. Manuel Gomez Rodriguez. Details of his talk can be found below.
Title: “Improving Decision Making with Machine Learning, Provably”
Abstract: Automated decision support systems promise to help human experts solve tasks more efficiently and accurately. However, existing systems typically require experts to understand when to cede agency to the system or when to exercise their own agency. Moreover, if the experts develop a misplaced trust in the system, their performance may worsen. In this talk, I will discuss the development of automated decision support systems that, by design, do not require experts to understand when each of their recommendations is accurate to improve their performance. Moreover, I will present both theoretical and experimental results that demonstrate that such decision support systems are robust to the accuracy of the machine learning models they rely on, however, the amount of human effort they help reducing does depend on their accuracy.