9 papers
How Many Domains Suffice for Domain Generalization? A Tight Characterization via the Domain Shattering Dimension
Cynthia Dwork, Lunjia Hu, Han Shao
We study a fundamental question of domain generalization: given a family of domains (i.e., data distributions), how many randomly sampled domains do we need to collect data from in…
Differentially Private Verification of Distribution Properties
Elbert Du, Cynthia Dwork, Pranay Tankala +1
A recent line of work initiated by Chiesa and Gur and further developed by Herman and Rothblum investigates the sample and communication complexity of verifying properties of distr…
Efficient and Private Property Testing via Indistinguishability
Cynthia Dwork, Pranay Tankala
Given a small random sample of -bit strings labeled by an unknown Boolean function, which properties of this function can be tested computationally efficiently? We show an equiv…
Debiasing Functions of Private Statistics in Postprocessing
Flavio Calmon, Elbert Du, Cynthia Dwork +2
Given a differentially private unbiased estimate of a statistic , we wish to obtain unbiased estimates of functions of , such as , solely t…
Inducing Efficient and Equitable Professional Networks through Link Recommendations
Cynthia Dwork, Chris Hays, Lunjia Hu +2
Professional networks are a key determinant of individuals' labor market outcomes. They may also play a role in either exacerbating or ameliorating inequality of opportunity across…
Differentially Private Learning Beyond the Classical Dimensionality Regime
Cynthia Dwork, Pranay Tankala, Linjun Zhang
We initiate the study of differentially private learning in the proportional dimensionality regime, in which the number of data samples and problem dimension approach infin…