Statistical Learning Theory

VC dimension, Rademacher complexity, and PAC-Bayes.


field tier

Statistical Learning Theory. VC dimension, Rademacher complexity, and PAC-Bayes.

Foundations and canonical references

The standard treatments of statistical learning theory approach the subject from complementary angles. Vapnik, Statistical Learning Theory (1998) provides historical context and an early systematic exposition of the material. Mohri, Foundations of Machine Learning (2018) is the anchor reference for the subject and lays out the core definitions, theorems, and worked examples that practitioners return to.

Open methodological questions for statistical learning theory include sharpening the bridges between foundational theory and computational practice, extending classical results to broader or more structured settings, and integrating the techniques surveyed above with adjacent mathematical disciplines. The references listed in this page are the entry points that current work builds on.

Prerequisites

Sources

  • textbook · historical · 1998
    Statistical Learning Theory
    vapnik-1998
  • textbook · primary · 2018
    Foundations of Machine Learning
    mohri-2018, rostamizadeh-2018, talwalkar-2018

In context

Where this topic sits in the prerequisite graph. Click any node to jump.

Open in full atlas →


Review this topic

This page was drafted by an agent and is waiting on expert review. Spotted a wrong prerequisite, a missing concept, a misattributed source, or a factual slip? Tell us — your review opens a tracked issue maintainers act on.