STAT 535: Statistical Machine Learning (2025 Autumn)

Lecture Notes

Lecture 01: Review on probability and statistics
- view accessible HTML

Lecture 02: Likelihood models
- view accessible HTML
- Also see this note.

Lecture 03: Generative models: mixture, variational, and flows
- view accessible HTML
- Major update: VAE, diffusion model, and normalizing flows.
- Also see this note.

Lecture 04: Linear regression and penalization
- view accessible HTML
- Minor update: clarifying typos.

Lecture 05: Graph and networks
- view accessible HTML

Lecture 06: Density estimation
- view accessible HTML
- Major update: Holder smoothness, derivative, and sampling from KDE.

Lecture 07: Nonparametric regression
- view accessible HTML
- Major update: Plug-in and local least square methods, general basis regression, neural nets.

Lecture 08: Classification
- view accessible HTML

Lecture 09: Clustering
- view accessible HTML

Lecture 10: Dimension reduction
- view accessible HTML

Lecture 11: Monte Carlo methods
- view accessible HTML

Lecture 12: The bootstrap
- view accessible HTML
- Major update: different variants of bootstrap and CI’s, Lindeberg-Feller’s CLT.
- See this R-code generated by AI (Gemini 3.0).

Lecture 13: Missing data
- view accessible HTML

Lecture 14: Causal inference
- view accessible HTML

Accessible HTML is generated by converting the PDF to HTML via pandoc. Gemini AI wrote a simple script for me to run this conversion. See this page for introduction.


Interactive AI Study Assistant (Experimental)

To help you study, I have set up a custom NotebookLM AI Study Assistant for this course. This tool is an interactive AI trained strictly on our STAT 535 lecture notes.

Access the STAT 535 NotebookLM Here (Requires a Google account)

How to use it: You can ask the AI to explain difficult proofs, compare notation across lectures, or generate conceptual practice questions based on our class materials.

⚠️ Important Disclaimer: Generative AI models can occasionally misinterpret algebra or “hallucinate” mathematical properties. Always verify the AI’s derivations against the official lecture notes above.

I’d love to hear how it’s helping you learn this topic. Leave anonymous feedback here.

Copyright © 2013-2025 Yen-Chi Chen. All rights reserved.