Majorizing Measures, Codes, and Information

Explore a thought-provoking lecture on the intersection of information theory and machine learning, delivered by Maxim Raginsky from the University of Illinois, Urbana-Champaign. Delve into the concept of majorizing measures and their applications in coding theory and information processing. Gain insights into how these principles contribute to the development of trustworthy machine learning systems. Discover the connections between mathematical abstractions and practical applications in the field of artificial intelligence during this 36-minute presentation from the Simons Institute's series on Information-Theoretic Methods for Trustworthy Machine Learning.