How can a machine learn from data? How should we construct appropriate models? How do we design algorithms for inference? What are the fundamental design principles of datadriven learning and decisionmaking?
This course will help you answer these fundamental questions in machine learning from a probabilistic perspective. You will read and discuss research papers in probabilistic machine learning, including but not limited to research topics about
Aug. 23 
Lecture #1: Overview

Aug. 25 
Lecture #2: Probability Fundamentals

Aug. 30 
Lecture #3: Model Comparison

Sept. 1 
Lecture #4: Decision Theory

Sept. 6 
Lecture #5: Neural Networks

Sept. 8 
Paper Discussion #1

Sept. 13 
Lecture #6: Variational Inference

Sept. 15 
Paper Discussion #2

Sept. 20 
Lecture #7: Markov Chain Monte Carlo I

Sept. 22 
Paper Discussion #3

Sept. 27 
Lecture #8: Markov Chain Monte Carlo II

Sept. 29 
Paper Discussion #4

Oct. 4 
Lecture #9: Variational Autoencoder

Oct. 6 
Paper Discussion #5

Oct. 11 
October Break

Oct. 13 
Lecture #10: Energybased Models

Oct. 18 
Paper Discussion #6

Oct. 20 
Lecture #11: Diffusion Models

Oct. 25 
Paper Discussion #7

Oct. 27 
Lecture #12: Gaussian Processes

Nov. 1 
Paper Discussion #8

Nov. 3 
Lecture #13: Uncertainty Estimation and Calibration

Nov. 8 
Paper Discussion #9

Nov. 10 
Lecture #14: OutofDistribution Detection

Nov. 15 
Paper Discussion #10

Nov. 17 
Lecture #15: Bayesian Optimization

Nov. 22 
Paper Discussion #11

Nov. 24 
Thanksgiving Break

Nov. 29 
Lecture #16: Metalearning

Dec. 1 
Paper Discussion #12

Dec. 6 
Project Presentations #1

Dec. 8 
Project Presentations #2
