Motivated by real-life deployments of multi-round federated analytics wi...
Training machine learning models with differential privacy (DP) has rece...
We propose a new definition of instance optimality for differentially pr...
We study the problem of discrete distribution estimation in KL divergenc...
We study discrete distribution estimation under user-level local differe...
We study high-dimensional sparse estimation under three natural constrai...
We study the problem of distributed mean estimation and optimization und...
We study robust testing and estimation of discrete distributions in the
...
We propose and analyze algorithms to solve a range of learning tasks und...
We study goodness-of-fit and independence testing of discrete distributi...
We consider the task of estimating sparse discrete distributions under l...
We consider distributed inference using sequentially interactive protoco...
Le Cam's method, Fano's inequality, and Assouad's lemma are three widely...
Federated learning (FL) is a machine learning setting where many clients...
We consider the task of estimating the entropy of k-ary distributions fr...
The decentralized nature of federated learning makes detecting and defen...
Local differential privacy (LDP) is a strong notion of privacy for indiv...
We study goodness-of-fit of discrete distributions in the distributed
se...
We consider the problems of distribution estimation and heavy hitter
(fr...
We develop differentially private methods for estimating various
distrib...
We consider discrete distribution estimation over k elements under
ε-loc...