Every lesson in the Statistical Learning Theory slide course, in full text: 2 decks, 121 slides.
The Learning Problem and the Proof TemplateSession 1a of a master's statistical learning theory course, built for a student who follows algorithm proofs but not learning-theory ones: the formal setup, why empirical risk minimisation can fail, the finite realizable sample-complexity theorem presented as four named moves each mapped onto its algorithm-proof twin, and the PAC and agnostic PAC definitions with their quantifiers read in order.
Uniform Convergence, No Free Lunch, and VC DimensionSession 1b: Hoeffding's inequality and the one-over-root-m window, epsilon-representative samples and the four-inequality ERM lemma, the agnostic finite-class bound derived by re-running the five-step template with only one step changed, no-free-lunch and the bias-complexity decomposition, VC dimension with the two-half proof discipline for thresholds, intervals and rectangles, the fundamental theorem and its rates, and a five-question routine for reading a learning-theory paper.
Want this taught 1-on-1? Alexander tutors Statistical Learning Theory — $55/session, free consultation.