ECE586IC: Interplay between Control and Machine Learning (Fall 2026)

Course Information

• Instructor: Bin Hu (binhu7@illinois.edu)

• Term: Fall 2026

• Office Hours: By appointment, CSL 145

• Lectures: Tu/Th 12-1:20pm, ECEB 3015

• For a complete syllabus, see here.

Course Description

This advanced graduate course focuses on the interplay between control and machine learning. One half of the course focuses on tailoring control tools to study algorithms and network models in large-scale machine learning. In the other half of the course, students will study how to combine machine learning and model-based control methods for control design problems.

The following topics will be covered: empirical risk minimization; first-order methods for large-scale machine learning; stochastic optimization; dissipation inequality; jump system theory; Lur'e-Postnikov type Lyapunov functions; integral quadratic constraints; KYP Lemma; control-theoretic methods for designing certifiably robust neural networks; modern neural verifiers; reinforcement learning for control; control-oriented analysis tools for temporal difference learning and Q-learning; zeroth-order optimization and evolutionary strategies; policy gradient methods for robust control; Goldstein's subgradient method for H-infinity control; adversarial reinforcement learning; imitation learning for control; control barrier functions; diffusion models and generative AI for control; large language models (LLMs) for control.

Required Materials

There is no required textbook for the class. All course material will be presented in class and/or provided online. Links for relevant papers will be listed in the resource section of the course website.

Prerequisites

ECE 515, ECE 534, and ECE 490 are recommended, but not required.

Grading

40% regular homework sets (4 homework sets in total, 10% each); 20% in-class presentation; 40% written research report (detailed guidelines for the in-class presentation and the final project will be posted in the resource section).

Homework: There are 4 homework sets. Homework will be submitted in class. Discussion on homework problems is permitted; however, each student must write and submit independent solutions. Extensions will be granted with instructor approval in advance. Otherwise, late homework without such prior approval will not be accepted.