- Library Home /
- Search Collections /
- Open Collections /
- Browse Collections /
- BIRS Workshop Lecture Videos /
- Private hypothesis selection
Open Collections
BIRS Workshop Lecture Videos
BIRS Workshop Lecture Videos
Private hypothesis selection Bun, Mark
Description
We investigate the problem of differentially private hypothesis selection: Given i.i.d. samples from an unknown probability distribution P and a set of m probability distributions H, the goal is to privately output a distribution from H whose total variation distance to P is comparable to that of the best such distribution. We present several algorithms for this problem which achieve sample complexity similar to those of the best non-private algorithms. These give new and improved learning algorithms for a number of natural distribution classes. Our results also separate the sample complexities of private mean estimation under product vs. non-product distributions.
Item Metadata
Title |
Private hypothesis selection
|
Creator | |
Publisher |
Banff International Research Station for Mathematical Innovation and Discovery
|
Date Issued |
2019-07-11T13:34
|
Description |
We investigate the problem of differentially private hypothesis selection: Given i.i.d. samples from an unknown probability distribution P and a set of m probability distributions H, the goal is to privately output a distribution from H whose total variation distance to P is comparable to that of the best such distribution.
We present several algorithms for this problem which achieve sample complexity similar to those of the best non-private algorithms. These give new and improved learning algorithms for a number of natural distribution classes. Our results also separate the sample complexities of private mean estimation under product vs. non-product distributions.
|
Extent |
57.0 minutes
|
Subject | |
Type | |
File Format |
video/mp4
|
Language |
eng
|
Notes |
Author affiliation: Boston University
|
Series | |
Date Available |
2020-01-08
|
Provider |
Vancouver : University of British Columbia Library
|
Rights |
Attribution-NonCommercial-NoDerivatives 4.0 International
|
DOI |
10.14288/1.0387564
|
URI | |
Affiliation | |
Peer Review Status |
Unreviewed
|
Scholarly Level |
Researcher
|
Rights URI | |
Aggregated Source Repository |
DSpace
|
Item Media
Item Citations and Data
Rights
Attribution-NonCommercial-NoDerivatives 4.0 International