Advanced Optimization & Randomized Methods | CMU Graduate Course

Explore powerful algorithmic tools for tackling large-scale data problems in machine learning and optimization. Gain a solid foundation for research in this cutting-edge field.

Introduction

This course covers a variety of topics from optimization (convex, nonconvex, continuous and combinatorial) as well as streaming algorithms. The key aim is to make students aware of powerful algorithmic tools used for tackling large-scale data intensive problems. The topics covered are chosen to give students a solid footing for research in machine learning and optimization, while strengthening their practical grasp.

Highlights

• Covers foundational classical theory as well as cutting-edge material in large-scale optimization
• Focuses on making students aware of powerful algorithmic tools for tackling large-scale data problems
• Provides a solid footing for research in machine learning and optimization

Recommendation

This course is recommended for students with prior exposure to convex optimization and algorithms at a graduate level, as well as a strong working knowledge of linear algebra, analysis, probability, and statistics. Programming experience in high-level languages is also advantageous.