Aaron Roth: What Should We Trust in Trustworthy Machine Learning?

Abstract: Machine learning is impressive, but imperfect --- it makes errors. When we use ML predictions to take action, especially in high stakes settings, we want to be cognizant of this fact and take into account our probabilistic uncertainty. There are many ways of quantifying uncertainty, but what are they good for? We take the position that probabilistic predictions should be "trustworthy" in the sense that downstream decision makers should be guaranteed that acting as if the probabilistic predictions are correct should guarantee them high utility outcomes relative to anything else they could do with the predictions. We give algorithms for doing this and show a number of applications. Bio: Aaron Roth is the Henry Salvatori Professor of Computer and Cognitive Science, in the Computer and Information Sciences department at the University of Pennsylvania, with a secondary appointment in the Wharton statistics department. He is affiliated with the Warren Center for Network and Data Science, and co-director of the Networked and Social Systems Engineering (NETS) program. He is also an Amazon Scholar at Amazon AWS. He is the recipient of the Hans Sigrist Prize, a Presidential Early Career Award for Scientists and Engineers (PECASE), an Alfred P. Sloan Research Fellowship, an NSF CAREER award, and research awards from Yahoo, Amazon, and Google. His research focuses on the algorithmic foundations of data privacy, algorithmic fairness, game theory, learning theory, and machine learning. Together with Cynthia Dwork, he is the author of the book “The Algorithmic Foundations of Differential Privacy.” Together with Michael Kearns, he is the author of “The Ethical Algorithm”. OpenMined is a non-profit foundation creating open-source technology infrastructure that helps researchers get answers from data without needing a copy or direct access. Our community of technologists is building Syft: the public network for non-public information. Learn more → www.openmined.org Supported by the OpenMined Foundation, the OpenMined Community is an online ecosystem of over 17,000 technologists, researchers, and industry professionals keen to unlock 1000x more data in every scientific field and industry. Join us on Slack → slack.openmined.org LinkedIn → www.linkedin.com/company/openmined X/Twitter → x.com/openminedorg Facebook → fb.com/openminedorg