Beta. Content is under active construction and has not been peer-reviewed. Report errors on GitHub.Disclaimer

Shareable map · Bookmark this page

ML Theory Roadmap

The whole curriculum on one page. 491 topics across 6 layers, from measure-theoretic foundations through modern deep learning and the research frontier. Tier-1 landmarks are the 126 core pages worth reading first.

Layer 0A · Axioms

48 topics

Sets, functions, logic, linear algebra, real analysis, measure-theoretic basics.

Layer 0B · Infrastructure

22 topics

Measure theory, functional analysis, convex duality, numerical foundations.

Layer 1 · Core Tools

55 topics

Concentration, estimation, information theory, optimization primitives, CLT.

Foundations

Concentration Probability

Statistical Foundations

Statistical Estimation

Numerical Optimization

Optimization Function Classes

Algorithms Foundations

Learning Theory Core

ML Methods

Sampling MCMC

Training Techniques

Methodology

Numerical Stability

Calculus Objects

Layer 2 · Learning Theory

129 topics

ERM, VC, Rademacher, PAC, stability, kernels, uniform convergence.

Foundations

Concentration Probability

Statistical Foundations

Probability

Decision Theory

Numerical Optimization

Optimization Function Classes

Learning Theory Core

ML Methods

Regression Methods

Sampling MCMC

Training Techniques

Methodology

NLP Foundations

RL Theory

Reinforcement Learning

EM and Variants

Numerical Stability

Calculus Objects

Applied Math

Bootstrap Resampling

Systems

Layer 3 · ML Methods

114 topics

Regression, SVMs, neural nets, optimization, regularization, NTK.

Foundations

Mathematical Infrastructure

Concentration Probability

Statistical Foundations

Probability

Decision Theory

Numerical Optimization

Optimization Function Classes

Algorithms Foundations

Learning Theory Core

Modern Generalization

ML Methods

Sampling MCMC

Training Techniques

Methodology

LLM Construction

RL Theory

Reinforcement Learning

AI Safety

Applied Math

Systems

Layer 4 · Deep Learning

57 topics

Transformers, attention, training dynamics, double descent, scaling.

Statistical Foundations

Modern Generalization

Methodology

LLM Construction

RL Theory

Beyond Llms

AI Safety

Scientific ML

Number Theory ML

Layer 5 · Frontier

66 topics

RLHF, alignment, interpretability, reasoning, agents, scaling laws.

Modern Generalization

Methodology

LLM Construction

RL Theory

Beyond Llms

AI Safety

Model Timeline

How to use this map

Planned additions

AI-safety pages I want to add once the primary sources are stable enough to cite without guessing. Each needs the papers read carefully before the page goes up. Expect small batches over the coming months, not a bulk drop.

These are not auto-generated stubs. They land when the mental model is clean.