We consider the problem of learning high-dimensional, nonparametric and structured (eg,
Gaussian) distributions in distributed networks, where each node in the network observes an …

Multiple players are each given one independent sample, about which they can only provide
limited information to a central referee. Each player is allowed to describe its observed …

The large communication cost for exchanging gradients between different nodes
significantly limits the scalability of distributed training for large-scale learning models …

We consider parameter estimation in distributed networks, where each sensor in the network
observes an independent sample from an underlying distribution and has $ k $ bits to …

A central server needs to perform statistical inference based on samples that are distributed
over multiple users who can each send a message of limited length to the center. We study …

We consider distributed parameter estimation using interactive protocols subject to local
information constraints such as bandwidth limitations, local differential privacy, and restricted …

Abstract We present Rotated Adaptive Tetra-iterated Quantizer (RATQ), afixed-length
quantizer for gradients in first order stochasticoptimization. RATQ is easy to implement and …

Multiple users getting one sample each from an unknown distribution seek to enable a
central server to conduct statistical inference. However, each player can only provide limited …

We consider the problem of estimating high-dimensional and nonparametric distributions in
distributed networks, where each sensor in the network observes an independent sample …

Disparate treatment occurs when a machine learning model produces different decisions for
individuals based on a legally protected or sensitive attribute (eg, age, sex). In domains …