Главная
Study mode:
on
1
Introduction
2
Agenda
3
Differential Privacy
4
Other mechanisms
5
SGD
6
Use Cases
7
Generic amplification lemma
8
Generic amplification bomb
9
Sampling without replacement
10
Intuition
11
Technical result
12
Analysis
13
Comparison
14
Data Structure
15
Results
16
Proof
17
Divergences
18
Subsampling
Description:
Explore the concept of privacy amplification in data analysis through this 50-minute lecture by Yu-Xiang Wang from UC Santa Barbara. Delve into topics such as differential privacy, stochastic gradient descent, and sampling techniques. Examine the generic amplification lemma and its applications, as well as the technical aspects of sampling without replacement. Gain insights into various divergences and subsampling methods used in privacy-preserving data analysis. Understand the importance of privacy in the context of modern data science and learn about cutting-edge techniques for enhancing privacy in analytical processes.

Privacy Amplification by Sampling and Renyi Differential Privacy

Simons Institute
Add to list