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).
All events take place in the Calvin Lab auditorium.
Registration is required to attend this workshop. To submit your name for consideration, please register and await confirmation of your acceptance to the workshop before booking your travel. Space may be limited, and you are advised to register early.
Jayadev Acharya (Cornell University), Robert Ashmead (US Census Bureau), Jordan Awan (Pennsylvania State University), Nina Balcan (Carnegie Mellon University), Borja Balle (Amazon), Andres Felipe Barrientos (Duke University), Raef Bassily (Ohio State University), Kamalika Chaudhuri (UC San Diego), Rachel Cummings (Georgia Institute of Technology), Cynthia Dwork (Harvard University & Microsoft Research), Vitaly Feldman (Google), Rina Foygel (Stanford University), John Friedman (Brown University), Abhradeep Guha Thakurta (UC Santa Cruz), Vishesh Karwa (Ohio State University), Dan Kifer (Pennsylvania State University), Frauke Kreuter (University of Maryland), Philip LeClerc (US Census Bureau), Jing Lei (Carnegie Mellon University), Katrina Ligett (Hebrew University of Jerusalem), Ashwin Machanavajjhala (Duke University), Audra McMillan (Boston University), Shay Moran (UC San Diego), Kobbi Nissim (Georgetown University), Mijung Park (Max Planck Institute for Intelligent Systems, Tuebingen), Gillian Raab (University of Edinburgh), Matthew Reimherr (Pennsylvania State University), Alessandro Rinaldo (Carnegie Mellon University), Aaron Roth (University of Pennsylvania), Benjamin Rubinstein (University of Melbourne), Lalitha Sankar (Arizona State University), Anand Sarwate (Rutgers University), Or Sheffet (University of Alberta), Aleksandra Slavković (Pennsylvania State University), Adam Smith (Boston University), Shuang Song (UCSD), Thomas Steinke (IBM Almaden), Kunal Talwar (Google), Salil Vadhan (Harvard University), Martin Wainwright (UC Berkeley), Yu-Xiang Wang (UC Santa Barbara), Steven Wu (University of Minnesota Twin Cities)