Related papers: QoS-Nets: Adaptive Approximate Neural Network Infe…

The deployment of mixture-of-experts (MoE) large language models (LLMs) presents significant challenges due to their high memory demands. These challenges become even more pronounced in multi-tenant environments, where shared resources must…

This paper considers an aerial base station (aerial-BS) assisted terrestrial network where user mobility is taken into account. User movement changes the network dynamically which may result in performance loss. To avoid this loss,…

Quantum Neural Networks (QNNs) have shown significant value across domains, with well-trained QNNs representing critical intellectual property often deployed via cloud-based QNN-as-a-Service (QNNaaS) platforms. Recent work has examined QNN…

Optimizing the topology of networks is an important challenge across engineering disciplines. In energy systems, network reconfiguration can substantially reduce losses and costs and thus support the energy transition. Unfortunately, many…

Emerging reconfigurable optical communication technologies allow to enhance datacenter topologies with demand-aware links optimized towards traffic patterns. This paper studies the algorithmic problem of jointly optimizing topology and…

Quantization has become a mainstream compression technique for reducing model size, computational requirements, and energy consumption for modern deep neural networks (DNNs). With improved numerical support in recent hardware, including…

This paper addresses the critical challenge of managing Quality of Service (QoS) in cloud services, focusing on the nuances of individual tenant expectations and varying Service Level Indicators (SLIs). It introduces a novel approach…

Enabling low precision implementations of deep learning models, without considerable performance degradation, is necessary in resource and latency constrained settings. Moreover, exploiting the differences in sensitivity to quantization…

In this paper, we propose a novel optimal power allocation method that features a power limit function and is able to ensure more users reach the desired Quality-of-Service (QoS). In our model we use sigmoidal-like utility functions to…

Individual objects, whether users or services, within a specific region often exhibit similar network states due to their shared origin from the same city or autonomous system (AS). Despite this regional network similarity, many existing…

With the increasing application of machine learning (ML) algorithms in embedded systems, there is a rising necessity to design low-cost computer arithmetic for these resource-constrained systems. As a result, emerging models of computation,…

The high computational complexity associated with training deep neural networks limits online and real-time training on edge devices. This paper proposed an end-to-end training and inference scheme that eliminates multiplications by…

Reconfigurable intelligent surface (RIS) technology has recently emerged as a spectral- and cost-efficient approach for wireless communications systems. However, existing hand-engineered schemes for passive beamforming design and…

Resource-efficient convolution neural networks enable not only the intelligence on edge devices but also opportunities in system-level optimization such as scheduling. In this work, we aim to improve the performance of resource-constrained…

Neural networks have shown significant potential in solving partial differential equations (PDEs). While deep networks are capable of approximating complex functions, direct one-shot training often faces limitations in both accuracy and…

Recent progress in deep learning has been driven by increasingly larger models. However, their computational and energy demands have grown proportionally, creating significant barriers to their deployment and to a wider adoption of deep…

Reinforcement Learning is gaining attention by the wireless networking community due to its potential to learn good-performing configurations only from the observed results. In this work we propose a stateless variation of Q-learning, which…

How to reduce compute and memory requirements of neural networks (NNs) without sacrificing performance? Many recent works use sparse Mixtures of Experts (MoEs) to build resource-efficient large language models (LMs). Here we introduce…

A switched-capacitor matrix multiplier is presented for approximate computing and machine learning applications. The multiply-and-accumulate operations perform discrete-time charge-domain signal processing using passive switches and 300 aF…

Training convolutional neural network models is memory intensive since back-propagation requires storing activations of all intermediate layers. This presents a practical concern when seeking to deploy very deep architectures in production,…