Structure and Sensitivity in DP: Comparing K-Norm Mechanisms - TIB AV-Portal

Structure and Sensitivity in DP: Comparing K-Norm Mechanisms

00:00

3

Zugehöriges Material

Banff International Research Station (BIRS) for Mathematical Innovation and Discovery

Formale Metadaten

Titel

Structure and Sensitivity in DP: Comparing K-Norm Mechanisms

Alternativer Titel

Comparing K-Norm Mechanisms

Serientitel

Mathematical Foundations of Data Privacy (18w5189)

Anzahl der Teile

22

Autor

Mitwirkende

Slavkovic, Aleksandra

Lizenz

CC-Namensnennung - keine kommerzielle Nutzung - keine Bearbeitung 4.0 International:
Sie dürfen das Werk bzw. den Inhalt in unveränderter Form zu jedem legalen und nicht-kommerziellen Zweck nutzen, vervielfältigen, verbreiten und öffentlich zugänglich machen, sofern Sie den Namen des Autors/Rechteinhabers in der von ihm festgelegten Weise nennen.

Identifikatoren

10.5446/59288 (DOI)

Herausgeber

Banff International Research Station (BIRS) for Mathematical Innovation and Discovery

Erscheinungsjahr

Sprache

Inhaltliche Metadaten

Fachgebiet	Informatik Mathematik
Genre	Workshop/Interaktives Format Vorlesung

Serie

Mathematical Foundations of Data Privacy (18w5189)22 / 22

1

48:46

Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness

2

31:14

Privacy-Preserving GANs Support Clinical Data Sharing

3

23:02

Accuracy First: Selecting a DP Level for Accurate ERM

4

35:43

Differentially Private Hypothesis Testing and Property Estimation

5

40:34

Privately learning high-dimensional distributions

6

1:11:12

Geometric Algorithms for Query Release

7

1:09:48

Bayesian models for adaptive data analysis

8

40:59

Privacy Amplification by Iteration

9

27:26

Revisiting Differentially Private Matrix Completion

10

54:49

Privacy-preserving prediction

11

39:23

End-to-End Analysis of PATE

12

40:40

Individual Sensitivity Preprocessing for Data Privacy

13

32:34

Local Differential Privacy for Evolving Data

14

40:23

Generative Adversarial Privacy

15

1:03:12

PSI: A (differentially) private data-sharing interface

16

39:22

Differential Privacy for Functional Data Analysis

17

39:42

A Hybrid of Advocacy and Modeling for Differential Privacy

18

1:07:27

On Algorithmic Fairness Between Groups and Individuals

19

50:23

Concentrated Differential Privacy

20

34:14

Model-Agnostic Private Learning

21

38:43

Private k-Means with Constant Multiplicative Error

22

30:37

Structure and Sensitivity in DP: Comparing K-Norm Mechanisms

Automatisches Abspielen