Notes on the math & methods behind machine learning.
A small collection of cheatsheets and working notes — compact enough to carry, rigorous enough to trust.
-
LA
Linear Algebra & Differential Equations
A compact, rigorous cheatsheet of the linear algebra and differential equations needed for machine learning and quantitative research, with worked exercises.
-
PS
Probability & Statistics
A scholarly cheatsheet of probability and statistics fundamentals for ML and quantitative research, with worked exercises.
-
ML
Machine Learning & Deep Learning
A compact, rigorous reference for the machine learning and deep learning fundamentals needed in ML and quantitative research, with worked exercises.
-
RL
Reinforcement Learning
From bandits and MDPs through policy gradients and modern actor–critic methods.
-
DF
Diffusion Models
From Brownian motion and Itô calculus to score matching, DDPM, DDIM, classifier-free guidance and flow matching — the toolkit behind modern image generators.
-
MC
Mechanics & Optimal Control
Analytical mechanics and optimal control for robotics — Lagrangian and Hamiltonian dynamics, manipulator equations, Pontryagin, HJB, LQR, iLQR, MPC, Lyapunov stability.