download defense details:
{
pdf
}
MSc thesis defense presentation
Agamemnon Giannakopoulos defends his MSc thesis
| Date: | Tuesday, 28 Feb 2017 |
|---|---|
| Time: | 16:00 |
| Location: | School of Electrical and Computer Engineering (old buildings), 1.1.31 |
| Thesis title: | Learning Poisson Binomial Distributions with Differential Privacy |
| Committee: |
Thesis abstract
This thesis tries to leverage two major research areas. The first area concerns the Distribution Learning Theory and the second the Differential Privacy. More specific, given a highly efficient algorithm which learns with ε-accuracy a Poisson Binomial Distribution we try to study its Differential Privacy property. We show that the Algorithm achieves Differential Privacy under specific circumstances (regarding PBD nature). If the PBD close to a (n,k)-Binomial form the algorithm is Differential Privacy. If the PBD is close to a k-sparse form algorithm's privacy depends on PBD cardinality.