Graph learning methods, such as Graph Neural Networks (GNNs) based on gr...
Local differential privacy (LDP) is a powerful method for privacy-preser...
We study the mean estimation problem under communication and local
diffe...
Privacy and communication constraints are two major bottlenecks in feder...
We consider the federated frequency estimation problem, where each user ...
We introduce the Poisson Binomial mechanism (PBM), a discrete differenti...
Generative Adversarial Networks are a popular method for learning
distri...
We consider the problem of estimating a d-dimensional discrete distribut...
We introduce a novel anytime Batched Thompson sampling policy for multi-...
We study the asymptotic performance of the Thompson sampling algorithm i...
We consider the problem of estimating a d-dimensional s-sparse discrete
...
We study schemes and lower bounds for distributed minimax statistical
es...
We consider the processing of statistical samples X∼ P_θ by a
channel p(...
Since the inception of the group testing problem in World War II, the
pr...
Thompson sampling has been shown to be an effective policy across a vari...
The optimal transport problem studies how to transport one measure to an...
Two major challenges in distributed learning and estimation are 1) prese...
In this work, we consider the deterministic optimization using random
pr...
Multiclass classification problems are most often solved by either train...
We develop data processing inequalities that describe how Fisher informa...
The large communication cost for exchanging gradients between different ...
We consider the Courtade-Kumar most informative Boolean function conject...
Federated learning (FL) is a machine learning setting where many clients...
We consider a distributed logistic regression problem where labeled data...
We consider the problem of learning high-dimensional, nonparametric and
...
The primitive relay channel, introduced by Cover in 1987, is the simples...
We consider an extremal problem for subsets of high-dimensional spheres ...
We consider the probabilistic group testing problem where d random
defec...
The classical problem of supervised learning is to infer an accurate
pre...
We consider a communication channel where there is no common clock betwe...
We consider parameter estimation in distributed networks, where each nod...