Course

PHYS-512: Statistical physics of computation

Lectures in this course (83)

Explores the transition from sparse to dense graphs and their real-world applications.

Covers the Spin Glass Game, belief propagation, and message passing algorithms.

Compares random and symmetrical graph coloring in terms of cluster colorability and equilibrium.

Explores the statistical physics of clusters, focusing on complexity and equilibrium behavior.

Discusses the unified formulation of the generalized linear model and the optimization of loss functions.

Explores hidden variables, graphical models, and computational gaps in neural network learning.

Covers the concept of graphical models and joint probability distributions.

Explains probability distribution, entropy, and Gibbs free entropy, along with the Weiss model.

Explores variational methods in statistical physics and the Bethe Parisi Mézard approach.

Covers the Random Field Ising Model, discussing the concept of disorder and the process of finding the ground state.

Discusses self-organization in complex systems and emergent properties.

Covers Belief Propagation, a key method for both analysis and algorithm.

Covers the computation of Bethe free entropy and the interpretation of messages between variables and factors.