Week 11 — Model Selection and Learning Theory

Why does any of this work? The statistical learning theory that bounds generalization error.

ML  ·  schedule  ·  Week 11 of 12 ·  ← 10 ·  12 →

Week 11 — Model Selection and Learning Theory

Why does any of this work? The statistical learning theory that bounds generalization error.

Lecture

The PAC framework · VC dimension and uniform convergence · Rademacher complexity · the bias-variance decomposition rigorously · structural risk minimization · model selection via AIC, BIC, cross-validation.

Read before the lecture

  • Hastie, Tibshirani, Friedman, chapter 7

Problem set

PS6 — Learning theory

  1. Prove the basic VC dimension upper bound for half-spaces in $\mathbb{R}^d$.
  2. Derive a generalization bound using Rademacher complexity for a linear class.

Reference text for this week: chapter 11 of the bilingual notes — EN PDF · FR PDF.