Related papers: Learning Physical-Layer Communication with Quantiz…

Post-training quantization is a representative technique for compressing neural networks, making them smaller and more efficient for deployment on edge devices. However, an inaccessible user dataset often makes it difficult to ensure the…

We study distributed optimization problems over a network when the communication between the nodes is constrained, and so information that is exchanged between the nodes must be quantized. Recent advances using the distributed gradient…

Quantum teleportation have a central role in quantum information science and allows transferring of an unknown quantum state through entanglement and classical communication. Unfortunately, the interaction with external and internal noise…

Consider a collaborative task carried out by two autonomous agents that are able to communicate over a noisy channel. Each agent is only aware of its own state, while the accomplishment of the task depends on the value of the joint state of…

In this paper, we study a quantized feedback scheme to maximize the goodput of a finite blocklength communication scenario over a quasi-static fading channel. It is assumed that the receiver has perfect channel state information (CSI) and…

Quantizing deep networks with adaptive bit-widths is a promising technique for efficient inference across many devices and resource constraints. In contrast to static methods that repeat the quantization process and train different models…

This paper proposes and evaluates a new performance estimation method that leverages continual learning (CL) algorithms to carry out sequential simulation experiments for a feedback-based molecular communication protocol. As the protocol is…

In quantum communication feedback may be defined in a number of distinct ways. An analysis of the effect feedback has on the rate information may be communicated is given, and a number of results and conjectures are stated.

The use of low-bit quantization has emerged as an indispensable technique for enabling the efficient training of large-scale models. Despite its widespread empirical success, a rigorous theoretical understanding of its impact on learning…

Dynamic feedback linearization-based methods allow us to design control algorithms for a fairly large class of nonlinear systems in continuous time. However, this feature does not extend to their sampled counterparts, i.e., for a given…

In multi input multi output antenna systems, beamforming is a technique for guarding against the negative effects of fading. However, this technique requires the transmitter to have perfect knowledge of the channel which is often not…

Linearising the dynamics of nonlinear mechanical systems is an important and open research area. A common approach is feedback linearisation, which is a nonlinear control method that transforms the input-output response of a nonlinear…

We consider the problem of solving a distributed optimization problem using a distributed computing platform, where the communication in the network is limited: each node can only communicate with its neighbours and the channel has a…

We investigate a quantum coding for quantum communication over a PD (partially degradable) degradable quantum channel. For a PD channel, the degraded environment state can be expressed from the channel output state up to a degrading map. PD…

Information exchange in multi-agent systems improves the cooperation among agents, especially in partially observable settings. In the real world, communication is often carried out over imperfect channels. This requires agents to handle…

Quantum feedback is a technique for measuring a qubit and applying appropriate feedback depending on the measurement results. Here, we propose a new on-chip quantum feedback method where the measurement-result information is not taken from…

Deep learning has been recently applied to physical layer processing in digital communication systems in order to improve end-to-end performance. In this work, we introduce a novel deep learning solution for soft bit quantization across…

Communication has been known to be one of the primary bottlenecks of federated learning (FL), and yet existing studies have not addressed the efficient communication design, particularly in wireless FL where both uplink and downlink…

Quantification is the supervised learning task that consists of training predictors of the class prevalence values of sets of unlabelled data, and is of special interest when the labelled data on which the predictor has been trained and the…

Although deep neural networks are highly effective, their high computational and memory costs severely challenge their applications on portable devices. As a consequence, low-bit quantization, which converts a full-precision neural network…