Algorithms for Data Science
COMPSCI 2243
Subject & Catalog Number
Course Information
Description
This is a graduate topics class on theoretical aspects of modern machine learning. Unlike previous offerings of this course, this iteration will focus on recent developments in diffusion generative modeling. The course will explore foundational aspects (Itô processes, discretization analysis, connections to stochastic optimal control and stochastic localization, and the complexity of score estimation) as well as empirical aspects for which the associated theory is still nascent (consistency models, guided generation, the mystery of generalization, and diffusion language models).
Course Notes
This course was previously numbered CS 224.
Recommended Prep
Mathematical maturity and proficiency with proofs, probability, and linear algebra strongly recommended. Stat 110 and CS 1210/1240 (or equivalent) required, except with permission from the instructor.
Available for Harvard Cross Registration
