Privacy in Statistics and Machine Learning

Adam Smith
Jonathan Ullman

Up to course home
Spring 2021
Privacy in Statistics and Machine Learning

Spring 2021

All lecture videos can be found in this Google Drive folder.

Date Topics Deliverables
Tue 1/26 Lecture 1: Course Overview

Video: Watch these two MinutePhysics videos (1, 2). They introduce some of the course topics in the context of the US Census.
Lecture Slides
In-class Exercises
=== Unit 1: Reconstruction Attacks ===
BU: Thu 1/28
NEU: Fri 1/29
Lecture 2: Reconstruction Attacks I

Lecture Notes: pdf (up through 2.3)
Video: part 1, part 2
In-class Exercises: pdf
Tue 2/2 Lecture 3: Reconstruction Attacks II

Lecture Notes: pdf (2.4 onward)
Video: part 1, part 2
In-class Exercises: pdf
=== Unit 2: Differential Privacy Fundamentals ===
BU: Thu 2/4
NEU: Fri 2/5
Lecture 4: Differential Privacy Fundamentals I

Lecture Notes: pdf
Video: part 1, part 2, part 3, part 4
In-class Exercises: pdf
Homework 1 Out (Due Fri 2/12): pdf, tex
Tue 2/9 Lecture 5: Differential Privacy Fundamentals II

Lecture Notes: pdf
Video: part 1, part 2, part 3
In-class Exercises: pdf
=== Unit 3: The Algorithmic Toolkit ===
BU: Thu 2/11
NEU: Fri 2/12
Lecture 6: Exponential Mechanism and Report Noisy Max

Lecture Notes: pdf
Video: part 1, part 2, part 3, part 4,
In-class Exercises: pdf
Homework 1 Due Fri 2/12
Tue 2/16 No Class
BU: Thu 2/18
NEU: Fri 2/19
Lecture 7: Recap and Discuss Projects

Project Info: pdf
In-class Exercises: See Lectures 5 and 6.
Tue 2/23 Lecture 8: The Binary Tree Mechanism

Lecture Notes: pdf
Video: part 1, part 2
In-class Exercises: pdf
HW 2 out (Due Fri 2/12): pdf, tex
BU: Thu 2/25
NEU: Fri 2/26
Lecture 9: Approximate DP

Lecture Notes: pdf
Video: part 1, part 2
In-class Exercises: pdf
Tue 3/2 Lecture 10: Advanced Composition

Lecture Notes: pdf
Video: part 1, part 2
In-class Exercises: pdf
BU: Thu 3/4
NEU: Fri 3/5
Lecture 11: Private Empirical Risk Minimization

Lecture Notes: pdf
Video: part 1, part 2
In-class Exercises: pdf
Project proposals due Fri 3/5
Tue 3/9 Lecture 12: Private Gradient Descent

Lecture Notes: pdf
Video: part 1, part 2
In-class Exercises: pdf
=== Unit 4: Linear Query Release ===
BU: Thu 3/11
NEU: Fri 3/12
Lecture 13: Factorization Mechanisms

Lecture Notes: pdf (up to 2.3)
Video: part 1, part 2
In-class Exercises: pdf
Homework 2 Due Fri 3/12
Tue 3/16 Lecture 14: The Projection Mechanism

Lecture Notes: pdf (2.3 onward)
Video: part 1
In-class Exercises: pdf
BU: Thu 3/18
NEU: Fri 3/19
NO CLASS

Tue 3/23 Lecture 15: Online Learning and Multiplicative Weights

Lecture Notes: pdf (Sections 1 to 3.1)
Video: part 1, part 2, part 3, part 4
In-class Exercises: pdf
BU: Thu 3/25
NEU: Fri 3/27
Lecture 16: Synthetic Data Generation and Online Learning I

Lecture Notes (hand-written, from lecture): pdf
Video: part 1, part 2, part 3, part 4, part 5.
(There is also part 6, which you should watch for Tuesday, March 30.)
In-class excercises: pdf
Tue 3/30 Lecture 17: Two-Player Zero-Sum Games I

Lecture Notes: pdf (up to 1.3)
Video: part 1 (Only one video for Lec 17. Also watch part 6 from Lecture 16.)
In-class excercises: pdf
BU: Thu 4/1
NEU: Fri 4/2
Lecture 18: Two-Player Zero-Sum Games II

Lecture Notes: pdf (1.3 onward)
Video: part 1 part 2 part 3
In-class excercises: pdf
Project progress reports due Fri 4/2
Tue 4/6 Lecture 19: Synthetic Data in Practice
(Guest Lecture by Steven Wu)


Zoom lecture, no reading
BU: Thu 4/8
NEU: Fri 4/9
Lecture 20: The Limits of Privacy

Lecture Notes: pdf
Tue 4/13 Lecture 21: Private Statistical Inference

BU: Thu 4/15
NEU: Fri 4/16
Lecture 22: Privacy and Adaptive Data Analysis

Zoom lecture
Reading: blog post by Moritz Hardt
Tue 4/20 Lecture 23: Differential Privacy and the Census
(Guest Lecture by Aloni Cohen)


Zoom lecture, no reading
Slides: pdf
BU: Thu 4/22
NEU: Fri 4/23
Lecture 24

Project draft final reports due Fri 4/23
Tue 4/27 Project presentations

Thu 4/29
Project presentations

Project final reports due Fri 4/30