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

The rump session on Thursday evening will be held in the Whitecotton Room at the Hotel Shattuck Plaza. All other events will take place in the Calvin Lab Auditorium.

–
Coffee and Check-In
–
Opening Remarks
–
Selective Inference and False Discovery Rate I
Yoav Benjamini, Tel Aviv University
–
Break
–
Selective Inference and False Discovery Rate II
Yoav Benjamini, Tel Aviv University
–
Musings on False Discovery Rate
Omer Reingold, Microsoft Research
–
Lunch Break
–
Tutorial on Differential Privacy
Katrina Ligett, California Institute of Technology
–
Break
–
DP-WHERE: Differentially Private Modeling of Human Mobility
Rebecca Wright, Rutgers University
–
Real-time Aggregate Monitoring with Differential Privacy
Li Xiong, Emory University
–
Dual Query Release: A Practical Algorithm for Private Analysis of High Dimensional Data
Justin Hsu, University of Pennsylvania
–
Differential Privacy and Stochastic Gradient Descent
Anand Sarwate, Toyota Technological Institute, Chicago
–
Reception
–
Coffee and Check-In
–
Learning and DP
Jonathan Ullman, Harvard University
–
Break
–
Active Statistical Query Learning with Connections to Privacy
Nina Balcan, Georgia Institute of Technology
–
Lunch Break
–
From Stability to Differential Privacy
Abhradeep Guha Thakurta, Stanford University and Microsoft Research
–
Break
–
A Stability-based Validation Procedure for Differentially Private Machine Learning
Kamalika Chaudhuri (UC San Diego)
–
Privacy, Forward Stability and Online Learning
Adam Smith, Pennsylvania State University
–
Extremal Mechanisms for Differential Privacy
Pramod Viswanath, University of Illinois, Urbana-Champaign
–
Dinner Break
–
Rump Session I (Hotel Shattuck Plaza)
–
Break
–
Rump Session II (Hotel Shattuck Plaza)
–
Coffee and Check-In
–
Local Privacy and Minimax Rates
John Duchi (Stanford University)
–
Break
–
Sparse PCA in High Dimensions
Jing Lei, Carnegie Mellon University
–
Private Learning and Sanitization: Pure vs. Approximate Differential Privacy
Kobbi Nissim, Ben-Gurion University of the Negev
–
Lunch Break
–
DP in the Streaming Model
Sasho Nikolov, Rutgers University
–
Turning Privacy-Utility Trade-offs Using Policies and an Application to US Census
Ashwin Machanavajjhala, Duke University
–
Break
–
Differentially Private Empirical Risk Minimization
Prateek Jain, Microsoft Research India
–
Break
–
The Power of Linear Reconstruction Attacks
Shiva Kasiviswanathan, GE Global Research
–
Coffee and Check-In
–
DP for Graphs and Social Networks
Sofya Raskhodnikova, Pennsylvania State University
–
Break
–
Geometry of DP
Li Zhang, Microsoft Research
–
Lunch Break
–
From Matrix Completion to Private Singular Vector Computation and Back
Moritz Hardt (UC Berkeley)
–
Randomized Response for Private Principal Component Analysis
Kunal Talwar (Google)
–
Break
Wrap-up Discussion