|
Activity Number:
|
633
- Foundations of Data Science: Privacy-Preserving Inference
|
|
Type:
|
Invited
|
|
Date/Time:
|
Thursday, August 1, 2019 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Business and Economic Statistics Section
|
|
Abstract #300026
|
Presentation 1
Presentation 2
Presentation 3
|
|
Title:
|
Privacy-Preserving Prediction
|
|
Author(s):
|
Cynthia Dwork and Vitaly Feldman*
|
|
Companies:
|
Harvard University and Google
|
|
Keywords:
|
privacy;
learning;
sample complexity;
prediction;
stability
|
|
Abstract:
|
Ensuring differential privacy of models learned from sensitive user data is an important goal that has been studied extensively in recent years. It is now known that for some basic learning problems, especially those involving high-dimensional data, producing an accurate private model requires much more data than learning without privacy. At the same time, in many applications it is not necessary to expose the model itself. Instead users may be allowed to query the prediction model on their inputs only through an appropriate interface. Here we formulate the problem of ensuring privacy of individual predictions and investigate the overheads required to achieve it in several standard models of classification and regression.
|
Authors who are presenting talks have a * after their name.
