ORF 526 · Princeton · Fall 2026

Probability for
Modern Machine Learning

The Gaussian The semicircle
MW 10:40–12:00 25 sessions Sep 2 – Dec 7 No measure theory
Module I · Gaussians 13 sessions · Sep 2 – Oct 14
1Sep 2
Gaussians: definition and linear structure
  • Definition by the Fourier transform, and why not the density
  • Linear images, existence, rotational invariance
  • Uncorrelated and jointly Gaussian implies independent
  • Maximum entropy at fixed covariance
notes·hw 1
2Sep 7
Gaussians: conditioning as projection
  • Conditional expectation as orthogonal projection
  • The Schur complement, derived
  • Bayesian posteriors and ridge regression
  • Gaussian process regression
notes·hw 2
3Sep 9
CLT: Lindeberg's method
  • Maximum entropy, recalled from the homework; the entropic CLT stated
  • Lindeberg's swapping argument, proved
  • The Lindeberg condition as the Gaussian/Poisson boundary
  • NNGP: a wide network at initialization
notes·hw 3
4Sep 14
Stein's method
  • The Gaussian characterized by an identity, not a limit
  • Stein's equation; the CLT with a Berry–Esseen rate
  • Chen–Stein for Poisson; dependence
notes·hw 4
5Sep 16
Gaussian integration by parts: Wick's theorem
  • Stein's identity
  • Wick's theorem, by induction
  • Pairings, and which of them cross
6Sep 21
Semicircle law: the moment method
  • The empirical spectral distribution; traces as moments
  • Wick applied to tr M⁴; crossings suppressed by 1/N
  • Catalan numbers and the limit
7Sep 23
Semicircle law: resolvents
  • The Stieltjes transform and its inversion
  • Schur complement and the self-consistent equation
  • The density, obtained directly
  • Marchenko–Pastur
8Sep 28
Cumulants: distance from Gaussian
  • Cumulants; vanishing beyond the second characterizes the Gaussian
  • Additivity, and scaling under normalized sums
  • Rates for the CLT; cumulants as a perturbation parameter
9Sep 30
Gaussian processes: the geometric picture
  • A process on an index set T as a curve in a Hilbert space
  • Existence from any positive semidefinite kernel
  • The Karhunen–Loève expansion
10Oct 5
Gaussian processes: the canonical metric and maxima
  • The canonical pseudometric is distance in the Hilbert space
  • Suprema as support functions; Gaussian width
  • Sudakov and Dudley, stated
11Oct 7
Kac–Rice and zero sets
  • The area formula, invoked without proof
  • Rice's formula for stationary processes
  • Random trigonometric polynomials; Kac polynomials
12Oct 12
Random landscapes: counting critical points
  • Conditioned on ∇f = 0, the Hessian is a GOE matrix
  • log|det| as a spectral integral
  • Exponentially many, overwhelmingly saddles
13Oct 14
Midterm examination
  • Sessions 1–12, closed book
Module II · Dynamics, Deviations, Diffusion 12 sessions · Oct 26 – Dec 7
1Oct 26
Martingales: conditional expectation and definitions
  • Conditional expectation as projection
  • Filtrations and the tower property
  • The Doob decomposition
2Oct 28
Martingales: limit theorems
  • Doob's maximal inequality; convergence in L²
  • Optional stopping
  • The martingale central limit theorem
3Nov 2
Martingales: concentration
  • Azuma–Hoeffding and Freedman
  • Bounded differences
4Nov 4
SGD: stochastic approximation
  • Drift plus martingale difference
  • Robbins–Monro and the ODE method
5Nov 9
SGD: fluctuations and averaging
  • Asymptotic normality of the iterates
  • Polyak–Ruppert averaging
  • Concentration along the trajectory
6Nov 11
SGD: high-dimensional dynamics
  • A deterministic ODE plus a fluctuation term
  • The data covariance spectrum, through the resolvent
7Nov 16
Large deviations: energy versus entropy
  • Cramér's theorem by exponential tilting
  • The rate function as a competition
8Nov 18
Large deviations: Sanov's theorem
  • The method of types
  • Relative entropy as the rate function
  • The contraction principle
9Nov 23
Large deviations: Varadhan and examples
  • Varadhan's lemma and the Gibbs variational principle
  • Curie–Weiss and its phase transition
  • Hypothesis testing; escape from a basin
10Nov 30
Diffusion models: the forward process
  • Noising as a Gaussian channel
  • Tweedie's formula from integration by parts
  • Denoising as score estimation
11Dec 2
Diffusion models: score matching
  • The reverse chain
  • Denoising score matching
  • The DDPM objective
12Dec 7
Diffusion models: the PDE picture
  • Fokker–Planck and the heat equation
  • The Gaussian as fundamental solution
  • Time reversal; the variational bound