Advanced Optimization and Randomized Methods

Organizational Information

• Lectures: Monday and Wednesday, 3:00PM–4:30PM

• Location: Gates Hillman Center 4307

• Recitations: Tuesdays 5:30-6:30pm

• Location: GHC 4307

• Instructors: Alex Smola and Suvrit Sra

• TAs: Madalina Fiterau (ina.fiterau@gmail.com) and Yu-Xiang Wang (luke.yxwang@gmail.com)

• Grading Policy: Homeworks (50%), Project (48%), Scribing (2%)

• Office hours for Suvrit: email me.

Goals

This course will cover a variety of topics from optimization (convex, nonconvex, continuous and combinatorial) as well as streaming algorithms. The key aim of the course is to make the students aware of powerful algorithmic tools that are used for tackling large-scale data intesive problems. The topics covered are chosen to give the students a solid footing for research in machine learning and optimization, while strengthening their practical grasp. In addition to foundational classical theory, the course will also cover some cutting-edge material due to the rapidly evolving nature of large-scale optimization.

Prerequisites

Students entering the course are expected to have prior exposure to convex optimization and algorithms at a graduate level. It will be very useful to have a strong working knowledge of linear algebra, analysis, and to some extent probability and statistics. Programming in a couple of high-level languages will be of advantage.

Lectures and related material