ECE 5290
Distributed Optimization for Machine Learning and AI
This is a graduate-level course about theory, algorithms and applications of distributed optimization and machine learning. The course covers the basics of distributed optimization and learning algorithms and their performance analyses when they are used to solve large-scale distributed problems arising in AI, machine learning, signal processing, communication networks, and power systems.
Topics
- Be able to formulate optimization problems arising from machine learning, signal processing, and wireless communication tasks.
- Be able to implement numerically stable and scalable algorithms to solve practical optimization problems in large-scale learning and computing.
- Be able to quantify convergence rates and resource efficiency of optimization algorithms in terms of iteration, computation and communication counts.
- Be able to design, modify, and deploy optimization algorithms tailored to the structure and constraints of real-world learning and wireless computing systems. (For PhD students)
Official roster learning outcomes
Sources
- Course catalogue ↗2026-2027