Instructor Information

  • Instructor: Matias G. Delgadino
  • Office: PMA 10.160
  • Office hours: Tuesday 9:00–10:00 AM, Wednesday 2:00–3:00 PM
  • Contact: matias.delgadino@utexas.edu
  • TA: Lukas Stefan Taus
  • Office hours: Monday & Thursday 1:00–2:00 PM
  • Contact: l.taus@utexas.edu

Course Meetings

  • Lectures: Tuesday & Thursday, 3:30–5:00 PM in PMA 5.122

Course Website

Course Description

This course introduces the mathematical foundations necessary for understanding and applying machine learning techniques. Emphasis is placed on optimization, linear algebra, and probability. Weekly Python homework assignments and three midterms are included.

Prerequisites

Basic knowledge of linear algebra, calculus, and probability.

Grading

  • Homework Assignments: 40%
  • Midterm Exams: 60%

Accommodations

Students with disabilities may request academic accommodations from the Division of Diversity and Community Engagement (DDCE), Services for Students with Disabilities (SSD).

Suggested Books

  • Shalev-Shwartz, S., & Ben-David, S. (2014). Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press.
  • Gordan Zitkovic. Lecture notes for “Introduction to Stochastic Processes”. Link
  • Boyd, S., & Vandenberghe, L. (2004). Convex Optimization. Cambridge University Press.
  • Strang, G. (2016). Introduction to Linear Algebra. Wellesley-Cambridge Press.
  • Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.

Course Schedule

Date Lecture Topic Lecture Notes Suggested Reading
Tuesday, August 26 Introduction, Python Basics and Quiz Lecture Notes Syllabus, quiz
Thursday, August 28 Introduction to PCA and Compressed Sensing Lecture Notes Shalev-Shwartz & Ben-David, Ch. 23
Tuesday, September 2 Linear Algebra Review Lecture Notes Strang, Ch. 1–2
Thursday, September 4 Rank, Projections, Eigenvalues Lecture Notes Strang, Ch. 3–5
Tuesday, September 9 Matrix Decompositions Lecture Notes Strang, Appendix C
Thursday, September 11 PCA Lecture Notes Shalev-Shwartz & Ben-David, Ch. 23
Tuesday, September 16 Compressed Sensing Lecture Notes Shalev-Shwartz & Ben-David, Ch. 23
Wednesday, September 19 Last Drop Day
Thursday, September 18 Linear Regression I: Least Squares Lecture Notes Shalev-Shwartz & Ben-David, Ch. 9
Tuesday, September 23 Linear Regression II: Non-linear Features Lecture Notes Shalev-Shwartz & Ben-David, Ch. 9
Thursday, September 25 Non-linear Regression: Neural Networks Lecture Notes Goodfellow et al., Ch. 6; Shalev-Shwartz & Ben-David, Ch. 20
Tuesday, September 30 Midterm I Linear Algebra
Thursday, October 2 Optimization Basics: Calculus Review Lecture Notes Boyd & Vandenberghe, Ch. 9; Strang, Ch. 18–19
Tuesday, October 7 Convexity and Gradient Descent Lecture Notes Boyd & Vandenberghe, Ch. 9
Thursday, October 9 Momentum Methods, Nesterov Acceleration Lecture Notes Boyd & Vandenberghe, Ch. 9
Tuesday, October 14 Support Vector Machines (SVM) Lecture Notes Shalev-Shwartz & Ben-David, Ch. 12
Thursday, October 16 SVM: Dual Formulation Lecture Notes Shalev-Shwartz & Ben-David, Ch. 15
Tuesday, October 21 SVM: Kernel Methods Lecture Notes Shalev-Shwartz & Ben-David, Ch. 16
Thursday, October 23 Graphs: Adjacency Matrix Lecture Notes Shalev-Shwartz & Ben-David, Ch. 22
Tuesday, October 28 Clustering: K-means Lecture Notes Shalev-Shwartz & Ben-David, Ch. 22
Thursday, October 30 Midterm II Optimization and SVM
Tuesday, November 4 Clustering: Spectral Clustering Lecture Notes Shalev-Shwartz & Ben-David, Ch. 22
Thursday, November 6 Random Walks on Graphs I Lecture Notes Zitkovic
Tuesday, November 11 Random Walks on Graphs II Lecture Notes Zitkovic
Thursday, November 13 Random Walks on Graphs III Lecture Notes Zitkovic
Tuesday, November 18 PageRank Lecture Notes Zitkovic
Thursday, November 20 Reversing a Random Walk Lecture Notes
Tuesday, November 25 Thanksgiving Break
Thursday, November 27 Thanksgiving Break
Tuesday, December 2 GAN Lecture Notes Goodfellow et al., Ch. 8
Thursday, December 4 Midterm III Clustering & Markov Chains