Dr. Jeong’s research focuses on building provably reliable machine learning (ML) systems using tools from information theory and coding theory. As ML systems are getting bigger, faster, and impacting more people, their reliability is challenged on many fronts. My research adapts and reinvents information-theoretic concepts for the context of reliable large-scale ML. To build reliability in machine metrics (e.g., computation time, accuracy), she marries coding theory and systems research to develop large-scale distributed algorithms that are resilient to unreliable or malicious nodes. To build reliability in human metrics (e.g., fairness, accountability), she closely collaborates with social scientists to investigate the fundamental limits of fairness of ML algorithms and develop discrimination mitigation strategies that can be used in practical ML pipelines.