COMP 545 - ADV TOPICS IN OPTIMIZATION
Long Title: ADVANCED TOPICS IN OPTIMIZATION: FROM SIMPLE TO COMPLEX ML SYSTEMS
Department: Computer Science
Grade Mode: Satisfactory/Unsatisfactory
Course Type: Seminar
Credit Hours: 3
Must be enrolled in one of the following Level(s):
Description: COMP 545 is a graduate-level course on optimization techniques and algorithms, as these are used in modern ML/AI/SP tasks. During this course, we will learn and study the above topics (both in depth and breadth). The course i) will focus on different objective classes (convex vs. non-convex objectives, with constraints or not, etc.), ii) will cover different optimization strategies within each class, iii) will study algorithmic choices based on computational resources (e.g., use of low-dimensional structures (when/why), asynchronous vs. synchronous algorithms, distributed algorithms, etc.) and iv) lastly, will study schemes that handle some specific, but well-spread optimization constraints (sparsity, low-rankness).The main objective of the course is to highlight optimization as a vital part of contemporary research in ML/AI/SP, and draw the attention of students to open-questions in related topics. In particular, the aim for students is to i) learn how to distinguish differences in research papers of related fields, ii) understand the connection between them and how researchers advance each area, and iii) be able to consider possible extensions of these works, as part of the final (open-ended) project of the course. Repeatable for Credit.