… quantization mechanism. Based on these properties, we propose a scheme following concepts
from … quantization [23], referred to as unviersal vector quantization for federated learning (…

In this paper, a new communication-efficient federated learning (FL) framework is proposed,
inspired by vector quantized compressed sensing. The basic strategy of the proposed …

… In this work, we tackle this challenge using tools from quantization theory. In particular, we
… quantization scheme for such setups. We show that combining universal vector quantization …

… To quantize the model updates, we use a vector quantization proposed by Eriksson [14] as
our main vector quantizer. A TCQ is defined by a set of states, a function describing the state …

… federated learning model to preserve local differential privacy. First, we provide two quantization
… We provide analysis of quantization noise for these methods. Next, we describe our …

… that combining universal vector quantized compressive … vector quantization on the
reconstruction process of compressive sensing. The quantization distortion caused by universal …

… In this context, federated ML plays a major role, ie learning schemes which … learning vector
quantization (LVQ) as particularly robust training method, and its extensions to metric learning …

… federated learning (FL) framework is proposed, which leverages ideas from vector quantized
… projected local model update is quantized by using a vector quantizer. The global model …

… enhancement and quantization (JoPEQ), which jointly implements lossy compression and
privacy enhancement in FL settings. In particular, JoPEQ utilizes vector quantization based on …

… We study federated learning (FL), which enables mobile devices to utilize their local datasets
to collaboratively train a global model with the help of a central server, while keeping data …