## EE364b - Convex Optimization IIInstructor: Mert Pilanci, pilanci@stanford.eduEE364b is the same as CME364b and was originally developed by Stephen Boyd ## AnnouncementsHomework 7 is out and due on May 30. You'll be working on convex optimization based ReLU neural networks, relaxations of cardinality constraints and sequential convex programming. Homework 6 is out and due on May 20. You'll experiment with conjugate gradient method, randomized preconditioners and Douglas-Rachford operator splitting to solve linear programs and learn about monotone operators. Homework 5 is out and due on May 6. You'll experiment with decomposition methods, ADMM, proximal gradient, and analyze the convergence of dual decomposition. Homework 4 is out and due on April 29. You'll learn about Bregman divergences, Mirror Descent and cutting plane methods. Homework 3 is out and due on April 22. You'll learn about stochastic subgradient method, stochastic programming and dealing with constrained optimization problems. Homework 2 is out and due on April 15. You'll learn about subgradient based methods for Lasso, heavy ball method, projection onto convex sets, line search for non-smooth functions and generalized subdifferentials of neural network losses. Homework 1 is out and due on April 8. You'll learn about multi-core distributed subgradient calculation using Dask, autodifferentiation in Pytorch and when it fails, and calculus rules for the subdifferential! The first lecture will be on Monday March 28, 1:30pm-3:00pm at Shriram Center BioChemE 104 The lectures will be recorded and be available to enrolled students Welcome to EE364b, Spring quarter 2021-2022!
## Course descriptionContinuation of 364A. Subgradient, cutting-plane, and ellipsoid methods. Decentralized convex optimization via primal and dual decomposition. Monotone operators and proximal methods; alternating direction method of multipliers. Exploiting problem structure in implementation. Convex relaxations of hard problems. Global optimization via branch and bound. Robust and stochastic optimization. Applications in areas such as control, circuit design, signal processing, machine learning and communications. This class will culminate in a final project. ## Prerequisites:EE364a - Convex Optimization I |