CS275P: Machine Learning with Generative Models

CS275P: Machine Learning with Generative Models

University of California, Irvine, Spring 2025

Prof. Erik Sudderth

CS275P explores methods for statistical machine learning with probabilistic generative models. We will study efficient inference algorithms based on optimization-based variational methods, and simulation-based Monte Carlo methods. Several approaches to learning from data will be covered, including conditional models for discriminative learning, Bayesian methods for controlling model complexity, probabilistic graphical models, and deep generative models such as variational autoencoders and diffusion models.  Methods will be motivated by applications including image and video analysis, text and language processing, sensor networks, autonomous robotics, computational biology, and social networks.

Course Materials

• Ed Discussion will be used for all course announcements, discussions, and questions.  All enrolled students should watch for important announcements and post questions (anonymously if you prefer) about course content.
• Lecture Calendar including readings, slides, and and how to access lecture recordings
• Discussion Calendar including links to Jupyter notebooks with example code
• Homework Assignments are distributed via Canvas, but submitted and graded via gradescope
• Homework Policies and Resources, including help with Python and the Collaboration and Academic Honesty Policy
• Final Project deadlines and requirements

Course Information

• Textbooks:  Probabilistic Machine Learning: Advanced Topics, Kevin P. Murphy, MIT Press, 2023.
  Bayesian Reasoning and Machine Learning, David Barber, Cambridge University Press, 2012.
• Lectures:  Tuesdays and Thursdays from 12:30-1:50pm in ICS 174.
• Discussions:  Fridays from 4:00-4:50pm in RH 101, led by the teaching assistants.
• Instructor:  Prof. Erik Sudderth. 
• Teaching Assistants:  Ian Harshbarger and Alfred Liu
• Office Hours: 
  • Mondays and Wednesdays 12:00-1:00pm on Zoom (https://uci.zoom.us/j/4495654571):  Alfred  Liu.
  • Tuesdays and Thursdays 3:00-4:00pm in DBH 3231:  Ian Harshbarger.
  • Wednesdays 3:30-5:00pm in DBH 4206:  Prof. Sudderth.
• Grading:  60% homework assignments, 40% final projects.

Course Prerequisites

A previous introductory course in machine learning (UCI CS273P).  Comfort with multivariable calculus and linear algebra.  Background in probability and statistics including exposure to maximum likelihood & Bayesian parameter estimation, evaluation methods (MSE, asymptotics), and hypothesis testing.  Python programming, and some experience with optimization algorithms, required for homeworks and projects.