Machine Learning (CSCI-GA.2565-001)

Course Description

The course covers general machine learning methods including generalized linear models, graphical models, causal inference, and reinforcement learning. There will be homework assignments along with a final project. Reading responses will be required every week along with a scribe of one lecture.

Lecture Location

Tuesday 4:55-6:55pm; Location: CIWW Room:102

Reading Assignments

• Introduction and Overview (9/6/22)
• Supervised Learning (9/13/22)
  • [Bishop PRML, Chapter 3.1]
• No Lecture: A Practical Session with Pytorch by Wanqian (9/20/22)
• A Bayesian Interlude (9/27/22)
  • [Bishop PRML, Chapter 3.2]
• Regularization + Generalized Linear Models (10/4/22)
  • [Murphy, Probabilistic Machine Learning: An Introduction, Chapter 12.1-12.3 new edition, Chapter 9.1-9.3 in 2012 edition]
• Neural Networks (10/18/22)
  • Deep Feedforward Networks
• Trees and Forests (10/25/22)
  • Random Forests
  • Gradient Boosting
• Latent Variable Models (11/1/22)
  • [Bishop PRML, Chapter 8.1-8.3]
• Computing with Latent Variable Models (11/8/22)
  • [Bishop PRML, Chapter 10.1-11.2]
• Deep Generative Models (11/15/22)
  • Generative Adversarial Nets
  • WaveNet
  • Deep Latent Gaussian Model
• Causal Inference (11/22/22)
  • Statistics and Causal Inference
  • [Morgan and Winship, Counterfactuals and Causal Inference: Methods And Principles For Social Research (Analytical Methods for Social Research), 2nd ed, Chapter 2]
• Reinforcement Learning (11/29/22)
  • Sutton and Barto, Reinforcement Learning: An Introduction, Chapter 1 and Chapter 13
  • Human-level Control through Deep Reinforcement Learning
• Cautionary Tales in Machine Learning + Concept Reviews (Victory Lap)(12/6/22)
  • Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imaging
• Class Presentations (12/13/22)

Assignments

In addition to the research project, a weekly reading response is due in class along with a couple of homework assignments. Students will be required to scribe one lecture in latex.

• Homework 0 Open date: 9/8/22 Due date: 9/22/22

• Homework 1 Open date: 9/29/22 Due date: 10/13/22

• Homework 2 Open date: 10/20/22 Due date: 11/3/22

• Homework 3 Open date: 11/10/22 Due date: 11/28/22

• Homework 4 Open date: 11/30/22 Due date: 12/13/22

Projects

There will be a research project due at the end of the term.

• Submit proposals 10/24/22

• Check-in with Staff: 10/24/22 - 11/4/22

• Project Presentations: 12/13/22

• Paper Submission: 12/18/22

Office Hours

• Rajesh Ranganath: Tuesday 3:40-4:40pm, online
• Wanqian Yang: Monday + Thursday 3:30-4:30pm, online