Private Learning and Sanitization: Pure vs. Approximate Differential Privacy

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=iKwzgtmGh9Y


Duration: 24:35
316 views
4

Kobbi Nissim, Ben-Gurion University of the Negev
Big Data and Differential Privacy
http://simons.berkeley.edu/talks/kobbi-nissim-2013-12-13



Other Videos By Simons Institute for the Theory of Computing


2014-01-24Delegated Quantum Computation
2014-01-24Introduction to Quantum Hamiltonian Complexity
2013-12-19DP for Graphs and Social Networks
2013-12-17Randomized Response for Private Principal Component Analysis
2013-12-17From Matrix Completion to Private Singular Vector Computation and Back
2013-12-17Geometry of DP
2013-12-17The Power of Linear Reconstruction Attacks
2013-12-17Differentially Private Empirical Risk Minimization
2013-12-17Turning Privacy-Utility Trade-offs Using Policies and an Application to US Census
2013-12-17DP in the Streaming Model
2013-12-17Private Learning and Sanitization: Pure vs. Approximate Differential Privacy
2013-12-17Sparse PCA in High Dimensions
2013-12-17Local Privacy and Minimax Rates
2013-12-17Extremal Mechanisms for Differential Privacy
2013-12-17Privacy, Forward Stability and Online Learning
2013-12-17A Stability-based Validation Procedure for Differentially Private Machine Learning
2013-12-17From Stability to Differential Privacy
2013-12-17Active Statistical Query Learning with Connections to Privacy
2013-12-17Learning and DP
2013-12-17Differential Privacy and Stochastic Gradient Descent
2013-12-17Dual Query Release: A Practical Algorithm for Private Analysis of High Dimensional Data


Tags:
Simons Institute
Big Data
UC Berkeley
computer science
theory of computing
Kobbi Nissim