Course Details
Contents
The current offering of the course during Aug-Nov 2026 will act as an introduction to differential privacy for statistics and machine learning. Course topics this year include Identification Attacks, Reconstruction Attacks, Differential Privacy, Randomized Response, Laplace Mechanism, Exponential Mechanism, Composition Theorems and Properties, Approximate Differential Privacy (Gaussian Mechanism), Applications to Statistics (Private mean estimation, Private Hypothesis Testing) and Applications to Machine Learning (Private Emperical Risk Minimization, Private Stochastic Gradient Descent). This course code is typically used to cover advanced topics in coding and information theory. In its last offering, Quantum error correction (QEC) was covered. Now QEC is being offered as a 3-credit course with course code EE5750 and in an offering earlier to this, MDS codes and applications to coded computation, coded gradient descent and coded fourier transform were covered.
References
1. Cynthia Dwork and Aaron Roth: The Algorithmic Foundations of Differential Privacy
2. Salil Vadhan: The Complexity Of Differential Privacy
3. Lectures on Differential Privacy by Gowtham Kamath
4. Lectures on Differential Privacy by Adam Smith and Jonathan Ullmann
5. Joseph P. Near and Chike Abuah: Programming Differential Privacy