Explore a thought-provoking lecture on learning classification metrics from preference feedback, presented by Sanmi Koyejo from Stanford University. Delve into information-theoretic methods for trustworthy machine learning as part of the Simons Institute series. Gain insights into innovative approaches for improving classification accuracy and reliability through the use of preference-based feedback mechanisms. Discover how these techniques can enhance the performance and trustworthiness of machine learning models across various applications.