Statistical Physics and Learning - Florent Krzakala, Sorbonne Université
Alan Turing Institute via YouTube
Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore the intersection of statistical physics and machine learning in this insightful lecture by Florent Krzakala from Sorbonne Université. Delve into the cross-fertilization between statistics and computer science in the era of Big Data. Discover how statisticians are addressing the challenge of maintaining inferential accuracy within time constraints, while computer scientists model data as noisy measurements from underlying populations. Examine the development of algorithmic paradigms that form the foundation of modern machine learning, including gradient descent methods, generalization guarantees, implicit regularization strategies, and high-dimensional statistical models and algorithms. Gain valuable insights into the advances at the intersection of statistics and computer science in machine learning, focusing on underlying theory and practical applications. This 41-minute talk is part of a two-day conference featuring leading international researchers, aimed at faculty, postdoctoral researchers, and Ph.D. students interested in this cutting-edge area of research.
Syllabus
Statistical Physics and Learning - Florent Krzakala, Sorbonne Université
Taught by
Alan Turing Institute