CSCI 678 is USC's theoretical machine learning course (Fall 2026, Haipeng Luo), built around the core tools of statistical learning theory: Rademacher complexity, covering numbers, VC dimension and pseudo-dimension, chaining, and more. This Project collects structured study notes produced along the way — preview reports, lecture summaries, and concept clarifications — so each lecture is easy to prepare for and easy to revisit later.
1. How the notes are organized
Each lecture note follows a fixed structure: the problem the lecture solves, the core theorems with proof skeletons, canonical examples, common confusions, questions to bring to class, and a 30-minute pre-lecture review order. Formulas are rendered with KaTeX and follow the notation of the course slides.
2. Currently published
Each lecture has two companion documents: a detailed explanation report (section-by-section, filling in proof details) and a full translation of the slides (preserving the original numbering and structure).
- Lecture 1: Detailed Explanation | Full Translation — formalizing the learning problem, the statistical learning framework, the no-free-lunch theorem, online and partial-information learning.
- Lecture 2: Detailed Explanation | Full Translation — uniform convergence, symmetrization and Rademacher complexity, growth function and VC dimension.
- Lecture 3: Preview Report | Full Translation — covering numbers, Dudley's entropy integral, and pseudo-dimension.
Notes for later lectures will be added over time. Project news lives under Updates.