Governments and industries have widely adopted differential privacy as a...
Modern statistical estimation is often performed in a distributed settin...
Compact user representations (such as embeddings) form the backbone of
p...
We consider the problem of Learning from Label Proportions (LLP), a weak...
The streaming model of computation is a popular approach for working wit...
When working with user data providing well-defined privacy guarantees is...
We present a differentially private algorithm for releasing the sequence...
Data anonymization is an approach to privacy-preserving data release aim...
We propose and analyze a general-purpose dataset-distance-based utility
...
The rollout of new versions of a feature in modern applications is a man...
We present a new analysis of the problem of learning with drifting
distr...