Machine Learning is a field at the intersection of statistics, probability, computer science, and optimization. The field is motivated by problems that are not necessarily addressed by classical statistics: how to build a face-detection system, how to design a character-recognition program, how to best display ads on webpages, how to predict movie ratings for a user. Since data for such tasks are inherently large-scale, a focus of machine learning has been on computational demands as well as on statistical accuracy. A student proficient in machine learning should therefore be versatile in both statistics and optimization. The following coursework is proposed:

**Required:**

STAT 530: Probability

STAT 531: Stochastic Processes

STAT 550: Mathematical Statistics

ESE 504: Introduction to Optimization Theory

ESE 605: Modern Convex Optimization

CIS 520: Machine Learning

**Optional:**

STAT 542: Bayesian Methods and Computation

STAT 928: Statistical Learning Theory

NETS 412: Algorithmic Game Theory

CIS 511: Introduction to The Theory of Computation