YoVDO

How to Use Heuristics for Differential Privacy

Offered By: IEEE via YouTube

Tags

IEEE FOCS: Foundations of Computer Science Courses Machine Learning Courses Heuristics Courses Differential Privacy Courses

Course Description

Overview

Learn about differential privacy heuristics in this 22-minute IEEE conference talk. Explore the theory, results, and properties of differential privacy, as well as its modular design. Discover the analogy between differential privacy and machine learning, including the learning problem and perfect oracle concept. Examine heuristics such as universal identification, RSPM, and the Wiggle Method. Gain insights into privacy analysis and consider open questions in the field. Presented by Seth Neel, Aaron Roth, and Zhiwei Steven Wu, this talk provides a comprehensive overview of using heuristics for differential privacy applications.

Syllabus

Introduction
Theory
Results
Differential Privacy
Differential Privacy Properties
Modular Design
The Good News
Machine Learning Analogy
Learning Problem
Perfect Oracle
Heuristics
Universal Identification
RSPM
Wiggle Method
Comments
Privacy Analysis
Open Questions


Taught by

IEEE FOCS: Foundations of Computer Science

Tags

Related Courses

An Improved Exponential-Time Approximation Algorithm for Fully-Alternating Games Against Nature
IEEE via YouTube
Computation in the Brain Tutorial - Part 2
IEEE via YouTube
Computation in the Brain - Part 1
IEEE via YouTube
Spectral Independence in High-Dimensional Expanders and Applications to the Hardcore Model
IEEE via YouTube
Cookbook Lower Bounds for Statistical Inference in Distributed and Constrained Settings - Part 1
IEEE via YouTube