Optimization Theory and Machine Learning (Spring 2018, TBSI)

Instructor: Somayeh Sojoudi
Time: May 8-13, 9:20 am-12 pm
Location: TBSI, Shenzhen, China

Description

The course covers several topics on optimization theory, numerical algorithms, machine learning, and different applications. It provides a basic understanding of the area and yet identifies important challenging problems for research. In particular, the students learn about the role of convex and conic optimization in machine learning and data science (such as lasso type algorithms) and how to apply these techniques to real-world data for transportation, power systems and many others. The course also discusses the design of efficient algorithms for solving large-scale learning problems.

Textbook

  • Convex Optimization, Stephen Boyd and Lieven Vandenberghe, (available online)

Readings

Conic Optimization Theory: Convexification Techniques and Numerical Algorithms

Semidefinite Relaxations for Nonlinear Optimization Problems (pp. 20-29)

Convexification of Generalized Network Flow Problem with Application to Power Systems

Linear-Time Algorithm for Learning Large-Scale Sparse Graphical Models