Explore the intricacies of learning Ising models from varying sample sizes in this hour-long lecture by MIT's Costis Daskalakis. Delve into the challenges and techniques of learning and testing in high-dimensional spaces, focusing on the impact of sample quantity on model accuracy and efficiency. Gain insights into the mathematical foundations and practical applications of Ising models across different disciplines.
Learning Ising Models from One, Ten or a Thousand Samples
Overview
Syllabus
Learning Ising Models from One, Ten or a Thousand Samples
Taught by
Simons Institute
Related Courses
-
Model Building and Validation
2.0 -
Critical Phenomena Through the Lens of the Ising Model by Hugo Duminil-Copin
-
Scaling Limits and Universality of Ising and Dimer Models
-
Why Do Simple Models Work? Partial Answers from Information Geometry - Lecture 1
-
Federated Learning for Nonparametric Function Estimation - Framework and Optimality
-
Statistical Physics and Learning - Florent Krzakala, Sorbonne Université
