Spring 2019

Privacy and the Science of Data Analysis

Apr. 8Apr. 12, 2019

Add to Calendar


Vitaly Feldman (Google; chair), Kamalika Chaudhuri (UC San Diego), Aleksandra Slavkovic (Pennsylvania State University), Adam Smith (Pennsylvania State University), Martin Wainwright (UC Berkeley)

Modern data analysis relies on solutions to a diverse set of inference and prediction problems. Imposing differential privacy or other formal privacy constraints can have a substantial impact on the computational and statistical efficiency with which these problems can be solved. The first theme that this workshop will explore is the frontiers and challenges of solving the common data analysis tasks subject to formal privacy constraints, with a focus on algorithmic and lower bound techniques that illuminate the computational and statistical costs of private data analysis. The second theme of the workshop is the connections between differential privacy viewed as a type of stability and the notions of algorithmic stability studied in learning theory and statistics. This connection provides a promising direction for dealing with the risk of overfitting and false discovery that arise in the challenging adaptive data analysis setting. The workshop will explore these additional connections between the techniques and tools used in private data analysis and techniques aimed at ensuring validity and robustness of statistical data analyses.

Further details about this workshop will be posted in due course. Enquiries may be sent to the organizers workshop-privacy2 [at] lists [dot] simons [dot] berkeley [dot] edu (at this address).

Registration is required to attend this workshop. Space may be limited, and you are advised to register early. The link to the registration form will appear on this page approximately 10 weeks before the workshop. To submit your name for consideration, please register and await confirmation of your acceptance before booking your travel.