THEORY & ALGORITHMS FOR DATA SCIENCE

Prerequisites & course information

Requisites: ( COMP SCI 200 , 220 , placement into COMP SCI 300 , or STAT 340 ), ( MATH 320 , 340 , 341 , 345 , or 375 ), and ( STAT 311 , 333 , 340 , MATH/STAT 309 , 431 , MATH 331 , 531 , or I SY E 210 ), or graduate/professional standing Course Designation: Core GenEd - Mathematics & Quantitative Reasoning Level - Advanced L&S Credit - L&S Liberal Arts and Science Repeatable for Credit: No Last Taught: Spring 2026 Learning Outcomes: 1. Use and explain theoretical concepts in data science, such as concentration inequalities, learning, nonparametric distribution testing, optimization. Audience: Undergraduate 2. Use properties of high-dimensional random variables to perform tasks such as dimension reduction and separating mixtures of Gaussians Audience: Undergraduate 3. Use optimization algorithms such as gradient descent and stochastic gradient descent and analyze their computational complexity Audience: Undergraduate 4. Analyze sample complexity for basic learning tasks such binary linear classification, as well as computational complexity of algorithms for solving them Audience: Undergraduate 5. Analyze sample complexity of distribution testing tasks, such as testing uniformity and testing equivalence of discrete distributions Audience: Undergraduate Learning Outcomes: 1. Use and explain theoretical concepts in data science, such as concentration inequalities, learning, nonparametric distribution testing, optimization. Audience: Undergraduate 2. Use properties of high-dimensional random variables to perform tasks such as dimension reduction and separating mixtures of Gaussians Audience: Undergraduate 3. Use optimization algorithms such as gradient descent and stochastic gradient descent and analyze their computational complexity Audience: Undergraduate 4. Analyze sample complexity for basic learning tasks such binary linear classification, as well as computational complexity of algorithms for solving them Audience: Undergraduate 5. Analyze sample complexity of distribution testing tasks, such as testing uniformity and testing equivalence of discrete distributions Audience: Undergraduate