
Mathematical techniques from statistical physics have been applied with increasing success on problems form
computer science, statistics, machine learning. These methods are nonrigorous, but in several cases they were
proved to yield correct predictions. This course provides a working knowledge of these methods for nonphysicists.
No background in physics is required.
Topics might include:
The pspin model and tensor PCA
synchronization and the SherringtonKirkpatrick model
Sharp analysis of highdimensional regression
The Hopfield model of a neural network
Models on sparse random graphs
Class Times and Locations
Building 320, Room 109
Friday, 9:45AM12:45PM
