Basic Information

• Course: Mathematical Foundations of Data Science
• Syllabus

Lecture Notes and Slides

• Lecture 01: notes, slides
• Lecture 02: notes (contains exercises 01-04, due: January 19, 11:59 PM), slides
• Lecture 03: notes (contains exercises 05-07, due: January 24, 11:59 PM), slides
• Lecture 04: notes (contains exercises 08-10, due: January 27, 11:59 PM), slides
• Lecture 05: notes (contains exercise 11, due: January 31, 11:59 PM), slides
• Lecture 06: notes (contains exercises 12-13, due: February 3, 11:59 PM), slides
• Lecture 07: notes (contains exercise 14, due: February 8, 11:59 PM)
• Lecture 08: notes (contains exercises 15-18, due: February 15, 11:59 PM)
• Lecture 09: notes (contains exercises 19-20, due: February 19, 11:59 PM), slides
• Lecture 10: notes, slides
• Lecture 11: notes (contains exercise 21, due: February 22, 11:59 PM)
• Lecture 12: notes (contains exercises 22-23, due February 26, 11:59 PM), slides
• Lecture 13: notes, slides
• Lecture 14: notes, slides
• Lecture 15: notes
• Lecture 16: notes (contains exercises 24-26, due April 9, 11:59 PM)
• Guest lecture: Jianrong Wang on “Introduction of Machine Learning in Computational Biology,” slides
• Guest lecture: Yuying Xie on “Probabilistic Graphical Models,” slides
• Lecture 17: notes
• Lecture 18: notes (contains exercises 27-28, due April 13, 11:59 PM)
• Lecture 19: notes (contains exercises 29-30, due April 20, 11:59 PM)
• Lecture 20: notes (contains exercises 31-33, optional), slides
• Lecture 21: notes (contains exercise 34, optional)
• Lecture 22: notes
• Lecture 23: notes (contains exercises 35-36, optional)
• Lecture 24: notes (contains exercise 37, optional), slides
• Lecture 25: notes, slides
• Lecture 26: notes (contains exercises 38-40, optional), slides

Data

• MNIST: .mat file
• Yale Faces: .mat file
• Circles: .mat file
• House: .mat file
• Closed Curve: .mat file

Project timeline:

• April 5, 11:59 PM: Submit project proposal (1/2 – 1 page)
• April 16, 11:59 PM: Submit project progress report (1 – 3 pages)
• April 30, 11:59 PM: Submit project (3-5 pages)

Resources

There is no required textbook for the class. The course will, however, draw material from the following sources:

• Learning with Kernels, by Schölkopf and Smola. Available online through the MSU library.
• Foundations of Machine Learning, by Mohri, Rostamizadeh and Talwalkar. Available online through the MSU library.
• Topics in Mathematics of Data Science, MIT open course by Afonso Bandeira.
• The Elements of Statistical Learning, by Hastie, Tibshirani and Friedman. Available online here.
• Spectral Graph Theory, Yale course by Dan Spielman.
• Geometric Structure of High-Dimensional Data and Dimensionality Reduction, by Wang.