Overview
This is a graduate-level reading seminar on how machine learning can aid in computer system operation. In this course, we will explore the state of the art in how machine learning is being used in systems, why, and where there are opportunities for further advancement. The objectives of this course are:
- To understand the different types of systems problems to which machine learning can apply, understand the trajectory of the field both both the machine learning and systems side, and identify key open issues.
- To critically review research papers at the intersection of machine learning and systems.
- To explore research problems and investigate new ideas through a semester-long research project.
The course is structured around lectures by the instructor, and paper presentations by the students with open discussion. Students will form a project group (two or three students) and conduct a research project on applying machine learning to systems.
Topics include:
- Need for ML in systems
- Use of LLMs to improve system policies.
- Applications of ML in improving resource management (e.g., caching, congestion control, scheduling)
- Challenges in deploying ML in systems
- Ensuring robustness and reliability of ML in systems
Logistics
- Instructor: Sujay Yadalam
- Class hours: Tuesdays and Thursdays, 3:30 PM - 5:00 PM
- Location: PMA 5.114
- Office hours: TBD
- Contact: sujay@cs.utexas.edu
Course organization and grading
Paper Reviews
You are required to read and submit a response to the canvas assignment Ed discussion posted for each assigned paper reading. The reviews are due at 9 AM the day of each class.
Class participation and discussion
Active participation in class discussions is expected from all students. This includes asking questions, sharing insights, and engaging with the material presented.
Presentations
The discussion for each paper will be lead by one or more students (leaders). Leaders are expected to lead the discussion using slides (preferred) or a whiteboard. Leaders should discuss the required background, contributions of the paper, critiques, and future work. Post presentation, the leader is also responsible for running the discussion session with the aid of instructor.
Quick links
Course policies
Academic Integrity
All material you submit in this course (reading responses, project reports, and presentation materials) must be your own. If you use someone else's material, you must cite them properly and make it very clear which parts are your own work. If you are ever in doubt about whether something you intend to submit violates this policy, please contact me before doing so.
Excused absences and late submissions
If for any reason you need to miss class or the response deadline, please contact the instructor as soon as possible and at least one week in advance (unless it is an emergency). We will find a way to make sure that your class participation and reading response grade won't be affected.
Services for students with disabilities
The university is committed to creating an accessible and inclusive learning environment consistent with university policy and federal and state law. Please let me know if you experience any barriers to learning so I can work with you to ensure you have equal opportunity to participate fully in this course. If you are a student with a disability, or think you may have a disability, and need accommodations please contact Disability and Access (D&A). Please refer to D&A's website for contact and more information: http://diversity.utexas.edu/disability/. If you are already registered with D&A , please deliver your Accommodation Letter to me as early as possible in the semester so we can discuss your approved accommodations and needs in this course.