Interactive Fingerprinting Codes and the Hardness of Preventing False Discovery thumbnail
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Interactive Fingerprinting Codes and the Hardness of Preventing False Discovery

Published on Sep 17, 20151586 Views

We show an essentially tight bound on the number of adaptively chosen statistical queries that a computationally efficient algorithm can answer accurately given n samples from an unknown distribution.

Related categories

Chapter list

Interactive Fingerprinting Codes and the Hardness of Preventing False Discovery00:00
Motivation: False Discovery00:00
Problem: Data Over-Use00:21
Model: Statistical Queries01:15
Key Question [DFHPRR15]01:52
Our Results02:38
Intuition03:41