E1 260-O Optimization for Machine Learning and Data Science 3:1 (August 2022)

Course Instructor: Sundeep Prabhakar Chepuri, ECE

Course description: This is a 3:1 elective course for the M.tech (Online) ECE programme. The main goal of this course is cover optimization techniques suitable for problems that frequently appear in the areas of data science, machine learning, communications, and signal processing.

Syllabus
Convexity, canonical problems, gradient methods, accelerated Methods, proximal algorithms, subgradient methods, stochastic gradient descent and variants, Frank-Wolfe, alternating direction method of multipliers.

Textbooks / References

  1. A. Beck, First-Order Methods in Optimization, MOS-SIAM Series on Optimization, 2017.
  2. S. Bubeck, Convex Optimization: Algorithms and Complexity, Foundations and Trends in Optimization, 2015.
  3. S. Boyd and L. Vandenberghe, Convex Optimization, Cambridge University Press, 2004.
  4. S. Boyd, N. Parikh, and E. Chu, Distributed optimization and statistical learning via the alternating direction method of multipliers, Foundations and Trends in Machine Learning, Now Publishers Inc.

Prerequisites: Matrix theory, background in basic calculus and probability.

Grading:

  • Assignments: 30% (3 assignments)
  • Mid-term: 20%
  • Final project: 30%
  • Final exam: 20%