Algorithmic Machine Learning

4 units · Graduate courses (200-299)

Lecture, four hours; outside study, eight hours. In-depth examination of handful of ubiquitous algorithms in machine learning. Covers several classical tools in machine learning but more emphasis on recent advances and developing efficient and provable algorithms for learning tasks. Topics include low-rank approximations, online learning, multiplicative weights framework, mathematical optimization, outlier-robust algorithms, streaming algorithms. S/U or letter grading.