Phase 1 — Core Math Foundations

01 · Mathematical Foundations
02 · Linear Algebra Basics
04 · Calculus Fundamentals
05 · Multivariate Calculus

Phase 2 — Probabilistic Thinking

06 · Probability Theory
07 · Statistics

Phase 3 — Making Models Learn

08 · Optimization
09 · Information Theory

Phase 4 — Deeper Theory

03 · Advanced Linear Algebra
10 · Numerical Methods
11 · Graph Theory
12 · Functional Analysis

Phase 5 — ML Math in Practice

13 · ML Specific Math
14 · Math for Specific Models

Phase 6 — LLM Math

15 · Math for LLMs
16 · LLM Training Data Pipeline

Phase 7 — Production & Safety

17 · Evaluation and Reliability
18 · Alignment and Safety
19 · Production ML and MLOps

Phase 8 — Research Frontiers

20 · Fourier Analysis and Signal Processing
21 · Statistical Learning Theory
22 · Causal Inference
23 · Game Theory
24 · Measure Theory
25 · Differential Geometry

Cheatsheet Interview Prep Notation Guide ML Math Map Visualization Guide

© 2026 Math for LLMs

All Courses Math for LLMs

CHAPTER

18 · Alignment and Safety

This chapter contains the following subtopics:

01 · Instruction Tuning and SFT
02 · Preference Optimization RLHF and DPO
03 · Red Teaming and Safety Evaluations
04 · Policy and Guardrails
05 · Human in the Loop and Monitoring

← Previous 05 · Online Experimentation and AB Testing Next → 01 · Instruction Tuning and SFT