EE 378B – Inference, Estimation, and Information Processing

Andrea Montanari, Stanford University, Winter 2017

A large number of problems in machine learning and signal processing require to extract information from data that take the form of matrices or tensors. We will discuss general mathematical and algorithmic tools to address these problems: spectral algorithms, semidefinite programming relaxations, non-convex optimization methods.

Specific topics include: clustering; graph data analysis; matrix completion; graph localization; group synchronization; dimensionality reduction and manifold learning.

Class Times and Locations

  • Hewlett 201

  • Mon-Wed, 1:30-2:50pm

  • First lecture on Monday, January 9.

  • The final is a take-home exam, starting from March 16, 4 pm to March 17, 4 pm.