Skip to content
conftrace_
2012 NeurIPS NeurIPS 2012

A Simple and Practical Algorithm for Differentially Private Data Release

Abstract

We present a new algorithm for differentially private data release, based on a simple combination of the Exponential Mechanism with the Multiplicative Weights update rule. Our MWEM algorithm achieves what are the best known and nearly optimal theoretical guarantees, while at the same time being simple to implement and experimentally more accurate on actual data sets than existing techniques.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Security & Privacy
📈 Trend Setter - Differential Privacy
🧭 Keyword Pioneer - exponential mechanism
🐣 Hot Topic Early Bird - data privacy

Authors

Moritz Hardt, Katrina Ligett, Frank Mcsherry

Topics

Machine Learning > Optimization & Theory > Optimization Machine Learning > Application Areas > Privacy Security & Privacy > Differential Privacy Machine Learning > Learning Types > Differential Privacy

Keywords

differential privacy data release exponential mechanism privacy-preserving data release private data release data privacy multiplicative weight
Download PDF

More from NeurIPS 2012

All NeurIPS 2012 papers →
On-line Reinforcement Learning Using Incremental Kernel-Based Stochastic Factorization
Accelerated Training for Matrix-norm Regularization: A Boosting Approach
Supervised Learning with Similarity Functions
Persistent Homology for Learning Densities with Bounded Support
Proper losses for learning from partial labels
Predicting Action Content On-Line and in Real Time before Action Onset – an Intracranial Human Study