Timezone: »
Differentially Private Sampling from Distributions
Satchit Sivakumar · Marika Swanberg · Sofya Raskhodnikova · Adam Smith
We initiate an investigation of private sampling from distributions. Given a dataset with $n$ independent observations from an unknown distribution $P$, a sampling algorithm must output a single observation from a distribution that is close in total variation distance to $P$ while satisfying differential privacy. Sampling abstracts the goal of generating small amounts of realistic-looking data. We provide upper and lower bounds for the dataset size needed for this task for two natural families of distributions: arbitrary distributions on $\{1,\ldots ,k\}$ and product distributions on $\{0,1\}^d$. We demonstrate that, in some parameter regimes, private sampling requires asymptotically fewer observations than learning a description of $P$ nonprivately; in other regimes, however, sampling proves to be as difficult as private learning.
Author Information
Satchit Sivakumar (Boston University)
Marika Swanberg (Boston University)
Sofya Raskhodnikova (Pennsylvania State Univ University Park)
Adam Smith (Boston University)
More from the Same Authors
-
2021 : Nonparametric Differentially Private Confidence Intervals for the Median »
Joerg Drechsler · Ira Globus-Harris · Audra McMillan · Adam Smith · Jayshree Sarathy -
2021 : Multiclass versus Binary Differentially Private PAC Learning »
Satchit Sivakumar · Mark Bun · Marco Gaboradi -
2021 : Differentially Private Model Personalization »
Prateek Jain · J K Rush · Adam Smith · Shuang Song · Abhradeep Guha Thakurta -
2021 : The Flajolet-Martin Sketch Itself Preserves Differential Privacy: Private Counting with Minimal Space »
Adam Smith · Shuang Song · Abhradeep Guha Thakurta -
2021 : When Is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning? »
Gavin Brown · Mark Bun · Vitaly Feldman · Adam Smith · Kunal Talwar -
2021 : Covariance-Aware Private Mean Estimation Without Private Covariance Estimation »
Gavin Brown · Marco Gaboradi · Adam Smith · Jonathan Ullman · Lydia Zakynthinou -
2023 Poster: The Price of Differential Privacy under Continual Observation »
Palak Jain · Sofya Raskhodnikova · Satchit Sivakumar · Adam Smith -
2023 Oral: The Price of Differential Privacy under Continual Observation »
Palak Jain · Sofya Raskhodnikova · Satchit Sivakumar · Adam Smith -
2021 : Contributed Talks Session 1 »
Marika Swanberg · Samuel Haney · Peter Kairouz