Mathematical Foundation of Data Science and Machine Learning

This website is under construction. Course information is subject to change.

Course Objective: An introduction to various topics of modern data science and machine learning. Prerequisites include calculus, linear algebra, and probability theory at the undergraduate level.

Instructor: Shuyang LING (sl3635@nyu.edu)

Lecture Time/Location: 1:15PM - 2:30PM on Mondays and Wednesdays, PDNG 213

Discussion/Recitation: 1:15PM - 2:30PM on Fridays, PDNG 213. This part will be used to discuss course projects.

Office hours: Room 1162-3

• Time TBD

* We will meet on Zoom due to the shutdown of academic building.

Textbook: The course consists of various topics. I will provide lecture notes and reading materials throughout of the course. Here are several references:

• Foundations of Data Science by A. Blum, J. Hopcroft, and R. Kannan.

• High-Dimensional Probability: An Introduction with Applications in Data Science by R. Vershynin.

• High-Dimensional Statistics: A Non-Asymptotic Viewpoint by M. Wainwright.

• A Mathematical Introduction to Compressive Sensing by S. Foucart and H. Rauhut.

• The Elements of Statistical Learning: Data Mining, Inference and Prediction by T. Hastie, R. Tibshirani, and J. Friedman.

• Ten Lectures and Forty-Two Open Problems in the Mathematics of Data Science by A.S. Bandeira

• A Mathematical Introduction to Data Analysis by Y. Yao

• Spectral graph theory by D. Spielman

Grading policy:

• Homework 40%

• Final project 60%

Homework

Late homework will not be accepted. Only a subset of problems will be graded.

Course schedule: The slides will be updated after each lecture. It is the first time this course is taught. The notes inevitably contain typos.