AI for Algorithmic Reasoning and Optimization

Course information

  • Quarter: Fall 2025
  • Lecture time: Tuesdays and Thursdays 1:30-2:50pm
  • Lecture location: Y2E2 111
  • Prerequisites: Introductory course in machine learning (e.g., CS 221 or CS 229)

Description

Artificial intelligence is expanding the frontier of algorithm design, enabling new ways to reason about and solve complex optimization problems. This course explores how AI methods—ranging from graph neural networks and diffusion models to large language models—can be integrated into the algorithm design pipeline. We will study how to use machine learning to design new algorithms, enhance classical algorithms with data-driven components, and optimize algorithm performance in specific application domains. Topics will span both practical approaches, such as differentiable optimization and generative AI for combinatorial problems, to theoretical perspectives, including approximation guarantees and the limits of learned algorithms.

Course activities

  • Lectures: The course will include lectures which cover key technical tools used to develop and analyze ML/AI approaches to algorithmic reasoning and optimization. These include introductions to graph neural networks, mathematical optimization frameworks, and approximation algorithms.
  • Discussions: There will be discussion classes where we cover key recently-published papers.
  • Project: Students will complete a course project, in a group or individually.

Grading

Grading will be out of 100 points. The grading breakdowns are listed on the following pages:

  • A 200-level course on related topics was taught in 2024: [link]
  • A 300-level version of the course was taught in 2023, but this course will feature all-new papers: [link]