Vladimir Vapnik: Statistical Learning | Lex Fridman Podcast #5

Summary

This conversation with Vladimir Vapnik, a co-inventor of Support Vector Machines, explores the nature of reality and learning through the lens of statistics and mathematics. Vapnik discusses instrumentalism versus realism, drawing parallels to how machine learning models can be used for prediction or for deeper understanding of conditional probabilities, referencing Eugene Wigner's "Unreasonable Effectiveness of Mathematics in the Natural Sciences." The takeaway emphasizes that rigorous mathematical derivation, rather than intuition alone, is crucial for uncovering fundamental truths about reality.