Stat 369 – Methods From Statistical Physics

Andrea Montanari, Stanford University, Winter 2017

Mathematical techniques from statistical physics have been applied with increasing success on problems form computer science, statistics, machine learning. These methods are non-rigorous, but in several cases they were proved to yield correct predictions. This course provides a working knowledge of these methods for non-physicists. No background in physics is required.

Ttopics might include:

  • The p-spin model and tensor PCA

  • {mathbf Z}_2 synchronization and the Sherrington-Kirkpatrick model

  • The Hopfield model of a neural network

  • Models on sparse graphs: Random satisfiability

Class Times and Locations

  • McMurthy Art and Art History Building, Room 360

  • Tue-Thu, 12:00-1:20pm

  • First lecture on Tuesday, January 10