Privacy and the Science of Data Analysis

Program

Data Privacy: Foundations and Applications

Location

Calvin Lab auditorium

Date

Monday, Apr. 8 – Friday, Apr. 12, 2019

Back to calendar

Click on the titles of individual talks for abstract, slides and archived video.

9 – 9:30 a.m.

Coffee and Check-In

9:30 – 9:45 a.m.

Opening Remarks

9:45 – 10:30 a.m.

Locally Private Bayesian Inference for Count Models

Steven Wu (Carnegie Mellon University)

10:30 – 11:15 a.m.

Finite Sample Differentially Private Confidence Intervals

Vishesh Karwa (Ohio State University)

11:15 – 11:30 a.m.

Break

11:30 a.m. – 12:15 p.m.

Differential Privacy with Elliptical Stochastic Processes

Matthew Reimherr (Pennsylvania State University)

12:15 – 2 p.m.

Lunch

2 – 2:45 p.m.

Robust Statistics and Bias Correction: Ideas for Differential Privacy and Utility

Carlo Molinari (Pennsylvania State University)

2:45 – 3:15 p.m.

Break

3:15 – 4 p.m.

Differentially Private Inference for Binomial Data

Jordan Awan (Pennsylvania State University)

4 – 4:45 p.m.

The Structure of Optimal Private Tests for Simple Hypotheses

Audra McMillan (Boston University)

4:45 – 6 p.m.

Reception

8:30 – 9 a.m.

Coffee and Check-In

9 – 10 a.m.

Practical Difficulties in the Application of Differential Privacy for the Release of Large-Scale Public Data Products

Philip LeClerc (U.S. Census Bureau)

10 – 10:45 a.m.

Shrinkwrap: Differentially-Private Query Processing in Private Data Federations

Johes Bater (Northwestern University)

10:45 – 11:15 a.m.

Break

11:15 a.m. – 12 p.m.

Analyzing Administrative Data with Privacy Protection in Place

Frauke Kreuter (University of Maryland)

12 – 12:45 p.m.

Differentially Private Inference for Regression Coefficients

Andrés Felipe Barrientos (Duke University)

12:45 – 2:15 p.m.

Lunch

2:15 – 3 p.m.

Node Privacy, High-dimensional Graph Summaries, and Block Models

Adam Smith (Boston University)

3 – 3:45 p.m.

Optimality in Locally Private Estimation and Learning

John Duchi (Stanford University)

3:45 – 4:15 p.m.

Break

4:15 – 5:30 p.m.

PANEL: Statistical Theory, Privacy and Data Analysis

Aleksandra Slavkovic (Pennsylvania State University),
Anand Sarwate (Rutgers University),
Thomas Steinke (IBM Almaden),
I,
Bin Yu (UC Berkeley),
Yu-Xiang Wang

8:30 – 9 a.m.

Coffee and Check-In

9 – 9:45 a.m.

Differentially Private Change-Point Detection

Rachel Cummings (Columbia University)

9:45 – 10:30 a.m.

Bandit Learning under Differential Privacy

Or Sheffet (University of Alberta)

10:30 – 11 a.m.

Break

11 – 11:45 a.m.

Pufferfish Privacy Mechanisms for Correlated Data

Shuang Song (Google)

11:45 a.m. – 1:15 p.m.

Lunch

1:15 – 2 p.m.

Black-box Random Differential Privacy with Sensitivity Sampling

Ben Rubinstein (Melbourne University)

2 – 2:45 p.m.

The Privacy Blanket of the Shuffle Model

Borja Balle (Amazon)

2:45 – 3:15 p.m.

Break

3:15 – 4:30 p.m.

Open Problem Session

Mark Bun (Boston University)

8:30 – 9 a.m.

Coffee and Check-In

9 – 9:45 a.m.

Locally Private Statistical Inference: Communication, Samples, and Shared Randomness

Jayadev Acharya (Cornell University)

9:45 – 10:30 a.m.

Privacy Amplification by Sampling and Renyi Differential Privacy

Yu-Xiang Wang (UC Santa Barbara)

10:30 – 11 a.m.

Break

11 – 11:45 a.m.

Private Meta-Selection

Kunal Talwar (Apple Inc)

11:45 a.m. – 12:15 p.m.

Learning without Interaction Requires Separation

Vitaly Feldman (Apple)

12:15 – 1:45 p.m.

Lunch

1:45 – 2:30 p.m.

Private Boosting and Noise-tolerant Learning

Mark Bun (Boston University)

2:30 – 3:15 p.m.

Private Center Points and Learning of Halfspaces

Amos Beimel (BGU)

3:15 – 3:45 p.m.

Break

3:45 – 4:30 p.m.

Federated Heavy Hitters Discovery with Differential Privacy

Peter Kairouz (Google AI)

4:30 – 5:15 p.m.

Private Learning with Auxiliary Public Data

Raef Bassily (Ohio State University)

8:30 – 9 a.m.

Coffee and Check-In

9 – 9:45 a.m.

Is Interaction Necessary for Distributed Private Learning?

Abhradeep Guha Thakurta (Google DeepMind)

9:45 – 10:30 a.m.

Groups and Individuals in Fairness and Probability

Cynthia Dwork (Harvard University)

10:30 – 11 a.m.

Break

11 – 11:45 a.m.

Towards a Characterization of Differentially Private Learning

Shay Moran (Technion - Israel Institute for Technology)

11:45 a.m. – 1:30 p.m.

Lunch

1:30 – 2:15 p.m.

Smooth Sensitivity, Revisited

Thomas Steinke (IBM Almaden)

2:15 – 3 p.m.

On the Power of Interactivity in Local Differential Privacy

Aaron Roth (University of Pennsylvania)

3 – 3:30 p.m.

Break

3:30 – 4:15 p.m.

The Limits of Post-Selection Generalization

Uri Stemmer (Ben Gurion University)

4:15 – 5 p.m.

A Necessary and Sufficient Stability Notion for Adaptive Generalization

Moshe Shenfeld (Hebrew University)