Speaker: Florent Krzakala, EPFL
Talk title: Generalization in Machine Learning: Insights from Simple Models
Time: Tuesday, April 20, 8:10am-9:10pm (PT)
Abstract:
Working in high-dimensions allows one to use powerful theoretical methods from probability theory and statistical physics to obtain precise characterization for many simple machine learning problems. I will present and review some recent works in this direction, and discuss what they teach us in the broader context of generalization, double descent, and over-parameterization in modern machine learning problems.
Return to workshop schedule