Max-Planck-Institut für Informatik
max planck institut
informatik
mpii logo Minerva of the Max Planck Society
 

MPI-INF or MPI-SWS or Local Campus Event Calendar

<< Previous Entry Next Entry >> New Event Entry Edit this Entry Login to DB (to update, delete)
What and Who
Title:Differential Privacy as a Learning Problem
Speaker:Moritz Hardt
coming from:IBM Almaden
Speakers Bio:
Event Type:Lecture
Visibility:D1, D2, D3, D4, D5, RG1, SWS, MMCI
We use this to send out email in the morning.
Level:Public Audience
Language:English
Date, Time and Location
Date:Monday, 19 November 2012
Time:13:00
Duration:60 Minutes
Location:Saarbrücken
Building:E1 4 - MPI-INF
Room:024
Abstract

This talk is about privacy-preserving analysis of sensitive data. We are interested in algorithms that satisfy the strong privacy guarantee known as differential privacy.
We show how to interpret differentially private data analysis as a learning problem. We use this connection to give several powerful algorithms for this task.
We conclude with the main algorithmic challenges that remain open.

I will assume no knowledge of differential privacy.

Contact
Name(s):Kurt Mehlhorn
Video Broadcast
Video Broadcast:NoTo Location:
Tags, Category, Keywords and additional notes
Note:
Attachments, File(s):

Created by:Kurt Mehlhorn/AG1/MPII/DE, 05/25/2012 04:52 PMLast modified by:Uwe Brahm/MPII/DE, 11/19/2012 06:01 AM
  • Kurt Mehlhorn, 11/15/2012 08:55 AM
  • Kurt Mehlhorn, 05/25/2012 04:52 PM -- Created document.