Concept
Belief propagation
Related lectures (29)
Noisy Gradient Descent Algorithms
Explores noisy gradient descent algorithms and their performance in high-dimensional optimization problems.
Gaussian Acyclic Models: Linearity and Identifiability
Covers Gaussian Acyclic Models focusing on linearity and identifiability.
Stochastic Block Model: Community Detection
Covers the Stochastic Block Model for community detection.
Committee Machine: Statistical Physics Approach
Explores hidden variables, graphical models, and computational gaps in neural network learning.
Graphical Models: Probability Distributions and Factor Graphs
Covers graphical models for probability distributions and factor graphs representation.
Cavity method and Approximate Message Passing
Explores the cavity method, Approximate Message Passing, and phase transitions in probabilistic models.
Belief Propagation in Stochastic Block Models
Covers the application of Belief Propagation in Stochastic Block Models, focusing on simplifying the process and solving it step by step.
Cavity Method: Mean Field Theory
Explores the Cavity Method in Mean Field Theory, analyzing spins in an external field within a graph.
Belief Propagation for Graph Coloring
Explores Belief Propagation for graph coloring and its convergence properties.
Graphical Models: Representing Probabilistic Distributions
Covers graphical models for probabilistic distributions using graphs, nodes, and edges.