Font size: Αα Αα Αα hide gadgets
You are here: Defenses » Φεβρουάριος 2017 » Αγαμέμνων Γιαννακόπουλος
download defense details: { pdf }

MSc thesis defense presentation

Αγαμέμνων Γιαννακόπουλος defends his MSc thesis

Date: Τρίτη, 28 Φεβ 2017
Ώρα: 16:00
Location: Σχολή Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών, ΕΜΠ (παλαιά κτήρια), 1.1.31
Thesis title: Learning Poisson Binomial Distributions with Differential Privacy

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.


Web standards: XHTML1.0, CSS3.
© 1996 – 2018 MPLA: Graduate program in Logic, Algorithms and Computation.
Contact the webmaster.