arXiv subjects

Nikolaos Pappas

Publications and source records attributed to Nikolaos Pappas.

At least 145 records · Page 8Linked to original sources

arXiv2022

A Perspective on Time towards Wireless 6G

With the advent of 5G technology, the notion of latency got a prominent role in wireless connectivity, serving as a proxy term for addressing the requirements for real-time communication. As wireless systems evolve towards 6G, the ambition to immerse the digital into the physical reality will increase. Besides making the real-time requirements more stringent, this immersion will bring the notions of time, simultaneity, presence, and causality to a new level of complexity. A growing body of research points out that latency is insufficient to parameterize all real-time requirements. Notably, one such requirement that received a significant attention is information freshness, defined through the Age of Information (AoI) and its derivatives. The objective of this article is to investigate the general notion of timing in wireless communication systems and networks and its relation to effective information generation, processing, transmission, and reconstruction at the senders and receivers. We establish a general statistical framework of timing requirements in wireless communication systems, which subsumes both latency and AoI. The framework is made by associating a timing component with the two basic statistical operations, decision and estimation. We first use the framework to present a representative sample of the existing works that deal with timing in wireless communication. Next, it is shown how the framework can be used with different communication models of increasing complexity, starting from the basic Shannon one-way communication model and arriving to communication models for consensus, distributed learning, and inference. Overall, this paper fills an important gap in the literature by providing a systematic treatment of various timing measures in wireless communication and sets the basis for design and optimization for the next-generation real-time systems.

cs.IT↗

arXiv2022

Semantics-Aware Source Coding in Status Update Systems

We consider a communication system in which the destination receives status updates from an information source that observes a physical process. The transmitter performs semantics-empowered filtering as a means to send only the most "important" samples to the receiver in a timely manner. As a first step, we explore a simple policy where the transmitter selects to encode only a fraction of the least frequent realizations of the observed random phenomenon, treating the remaining ones as not informative. For this timely source coding problem, we derive the optimal codeword lengths in the sense of maximizing a semantics-aware utility function and minimizing a quadratic average length cost. Our numerical results show the optimal number of updates to transmit for different arrival rates and encoding costs and corroborate that semantic filtering results in higher performance in terms of timely delivery of important updates.

cs.IT↗

arXiv2022

QoS Aware Robot Trajectory Optimization with IRS-Assisted Millimeter-Wave Communications

In this paper, we consider the motion energy minimization problem for a robot that uses millimeter-wave (mm-wave) communications assisted by an intelligent reflective surface (IRS). The robot must perform tasks within given deadlines and it is subject to uplink quality of service (QoS) constraints. This problem is crucial for fully automated factories that are governed by the binomial of autonomous robots and new generations of mobile communications, i.e., 5G and 6G. In this new context, robot energy efficiency and communication reliability remain fundamental problems that couple in optimizing robot trajectory and communication QoS. More precisely, to account for the mutual dependency between robot position and communication QoS, robot trajectory and beamforming at the IRS and access point all need to be optimized. We present a solution that can decouple the two problems by exploiting mm-wave channel characteristics. Then, a closed-form solution is obtained for the beamforming optimization problem, whereas the trajectory is optimized by a novel successive-convex optimization-based algorithm that can deal with abrupt line-of-sight (LOS) to non-line-of-sight (NLOS) transitions. Specifically, the algorithm uses a radio map to avoid collisions with obstacles and poorly covered areas. We prove that the algorithm can converge to a solution satisfying the Karush-Kuhn-Tucker conditions. The simulation results show a fast convergence rate of the algorithm and a dramatic reduction of the motion energy consumption with respect to methods that aim to find maximum-rate trajectories. Moreover, we show that the use of passive IRSs represents a powerful solution to improve the radio coverage and motion energy efficiency of robots.

cs.NI↗

arXiv2022

Holographic Observables at Large $d$

We study holographically non-local observables in field theories at finite temperature and in the large $d$ limit. These include the Wilson loop, the entanglement entropy, as well as an extension to various dual extremal surfaces of arbitrary codimension. The large $d$ limit creates a localized potential in the near horizon regime resulting in a simplification of the analysis for the non-local observables, while at the same time retaining their qualitative physical properties. Moreover, we study the monotonicity of the coefficient $α$ of the entanglement's area term, the so called area theorem. We find that the difference between the UV and IR of the $α$-values, normalized with the thermal entropy, converges at large $d$ to a constant value which is obtained analytically. Therefore, the large $d$ limit may be used as tool for the study and (in)validation of the renormalization group monotonicity theorems. All the expectation values of the observables under study show rapid convergence to certain values as $d$ increases. The extrapolation of the large $d$ limit to low and intermediate dimensions shows good quantitative agreement with the numerical analysis of the observables.

hep-th↗

arXiv2022

Semantics-Aware Active Fault Detection in Status Updating Systems

With its growing number of deployed devices and applications, the Internet of Things (IoT) raises significant challenges for network maintenance procedures. In this work we address a problem of active fault detection in an IoT scenario, whereby a monitor can probe a remote device in order to acquire fresh information and facilitate fault detection. However, probing could have a significant impact on the system's energy and communication resources. To this end, we utilize Age of Information as a measure of the freshness of information at the monitor and adopt a semantics-aware communication approach between the monitor and the remote device. In semantics-aware communications, the processes of generating and transmitting information are treated jointly to consider the importance of information and the purpose of communication. We formulate the problem as a Partially Observable Markov Decision Process and show analytically that the optimal policy is of a threshold type. Finally, we use a computationally efficient stochastic approximation algorithm to approximate the optimal policy and present numerical results that exhibit the advantage of our approach compared to a conventional delay-based probing policy.

cs.NI↗

arXiv2022

On-Demand AoI Minimization in Resource-Constrained Cache-Enabled IoT Networks with Energy Harvesting Sensors

We consider a resource-constrained IoT network, where multiple users make on-demand requests to a cache-enabled edge node to send status updates about various random processes, each monitored by an energy harvesting sensor. The edge node serves users' requests by deciding whether to command the corresponding sensor to send a fresh status update or retrieve the most recently received measurement from the cache. Our objective is to find the best actions of the edge node to minimize the average age of information (AoI) of the received measurements upon request, i.e., average on-demand AoI, subject to per-slot transmission and energy constraints. First, we derive a Markov decision process model and propose an iterative algorithm that obtains an optimal policy. Then, we develop an asymptotically optimal low-complexity algorithm -- termed relax-then-truncate -- and prove that it is optimal as the number of sensors goes to infinity. Simulation results illustrate that the proposed relax-then-truncate approach significantly reduces the average on-demand AoI compared to a request-aware greedy (myopic) policy and also depict that it performs close to the optimal solution even for moderate numbers of sensors.

eess.SP↗

arXiv2021

RIS-aided D2D Communication Design for URLLC Packet Delivery

In this paper, we consider a smart factory scenario where a set of actuators receive critical control signals from an access point (AP) with reliability and low latency requirements. We investigate jointly active beamforming at the AP and passive phase shifting at the reconfigurable intelligent surface (RIS) for successfully delivering the control signals from the AP to the actuators within a required time duration. The transmission follows a two-stage design. In the first stage, each actuator can both receive the direct signal from AP and the reflected signal from the RIS. In the second stage, the actuators with successful reception in the first stage, relay the message through the D2D network to the actuators with failed receptions. We formulate a non-convex optimization problem where we first obtain an equivalent but more tractable form by addressing the problem with discrete indicator functions. Then, Frobenius inner product based equality is applied for decoupling the optimization variables. Further, we adopt a penalty-based approach to resolve the rank-one constraints. Finally, we deal with the $\ell_0$-norm by $\ell_1$-norm approximation and add an extra term $\ell_1-\ell_2$ for sparsity. Numerical results reveal that the proposed two-stage RIS-aided D2D communication protocol is effective for enabling reliable communication with latency requirements.

cs.IT↗

arXiv2021

Performance Analysis of a MIMO System with Bursty Traffic in the presence of Energy Harvesting Jammer

This paper explores the role of multiple antennas in mitigating jamming attacks for the Rayleigh fading environment with exogenous random traffic arrival. The jammer is assumed to have energy harvesting ability where energy arrives according to Bernoulli process. The outage probabilities are derived with different assumptions on the number of antennas at the transmitter and receiver. The outage probability for the Alamouti space-time code is also derived. The work characterizes the average service rate for different antenna configurations taking into account of random arrival of data and energy at the transmitter and jammer, respectively. In many practical applications, latency and timely updates are of importance, thus, delay and Average Age of Information (AAoI) are the meaningful metrics to be considered. The work characterizes these metrics under jamming attack. The impact of finite and infinite energy battery size at the jammer on various performance metrics is also explored. Two optimization problems are considered to explore the interplay between AAoI and delay under jamming attack. Furthermore, our results show that Alamouti code can significantly improve the performance of the system even under jamming attack, with less power budget. The paper also demonstrates how the developed results can be useful for multiuser scenarios.

cs.IT↗

arXiv2021

Finetuning Pretrained Transformers into RNNs

Transformers have outperformed recurrent neural networks (RNNs) in natural language generation. But this comes with a significant computational cost, as the attention mechanism's complexity scales quadratically with sequence length. Efficient transformer variants have received increasing interest in recent works. Among them, a linear-complexity recurrent variant has proven well suited for autoregressive generation. It approximates the softmax attention with randomized or heuristic feature maps, but can be difficult to train and may yield suboptimal accuracy. This work aims to convert a pretrained transformer into its efficient recurrent counterpart, improving efficiency while maintaining accuracy. Specifically, we propose a swap-then-finetune procedure: in an off-the-shelf pretrained transformer, we replace the softmax attention with its linear-complexity recurrent alternative and then finetune. With a learned feature map, our approach provides an improved tradeoff between efficiency and accuracy over the standard transformer and other recurrent variants. We also show that the finetuning process has lower training cost relative to training these recurrent variants from scratch. As many models for natural language tasks are increasingly dependent on large-scale pretrained transformers, this work presents a viable approach to improving inference efficiency without repeating the expensive pretraining process.

cs.CL↗

arXiv2021

Sentence Bottleneck Autoencoders from Transformer Language Models

Representation learning for text via pretraining a language model on a large corpus has become a standard starting point for building NLP systems. This approach stands in contrast to autoencoders, also trained on raw text, but with the objective of learning to encode each input as a vector that allows full reconstruction. Autoencoders are attractive because of their latent space structure and generative properties. We therefore explore the construction of a sentence-level autoencoder from a pretrained, frozen transformer language model. We adapt the masked language modeling objective as a generative, denoising one, while only training a sentence bottleneck and a single-layer modified transformer decoder. We demonstrate that the sentence representations discovered by our model achieve better quality than previous methods that extract representations from pretrained transformers on text similarity tasks, style transfer (an example of controlled generation), and single-sentence classification tasks in the GLUE benchmark, while using fewer parameters than large pretrained models.

cs.CL↗

arXiv2021

Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Translation

Much recent effort has been invested in non-autoregressive neural machine translation, which appears to be an efficient alternative to state-of-the-art autoregressive machine translation on modern GPUs. In contrast to the latter, where generation is sequential, the former allows generation to be parallelized across target token positions. Some of the latest non-autoregressive models have achieved impressive translation quality-speed tradeoffs compared to autoregressive baselines. In this work, we reexamine this tradeoff and argue that autoregressive baselines can be substantially sped up without loss in accuracy. Specifically, we study autoregressive models with encoders and decoders of varied depths. Our extensive experiments show that given a sufficiently deep encoder, a single-layer autoregressive decoder can substantially outperform strong non-autoregressive models with comparable inference speed. We show that the speed disadvantage for autoregressive baselines compared to non-autoregressive methods has been overestimated in three aspects: suboptimal layer allocation, insufficient speed measurement, and lack of knowledge distillation. Our results establish a new protocol for future research toward fast, accurate machine translation. Our code is available at https://github.com/jungokasai/deep-shallow.

cs.CL↗

arXiv2021

Throughput and Age of Information in a Cellular-based IoT Network

This paper studies the interplay between device-to-device (D2D) communications and real-time monitoring systems in a cellular-based Internet of Things (IoT) network. In particular, besides the possibility that the IoT devices communicate directly with each other in a D2D fashion, we consider that they frequently send time-sensitive information/status updates (about some underlying physical processes) to their nearest base stations (BSs). By modeling the locations of the IoT devices as a bipolar Poisson Point Process (PPP) and that of the BSs as another independent PPP, we characterize the performance of the D2D links and status update links in terms of network throughput and Age-of-Information (AoI), respectively. We consider a maximum power constraint and distance-dependent fractional power control for all status update transmissions. Hence, the locations of the IoT devices allowed to send status updates are constrained to lie within the Johnson-Mehl cells. For this set-up, the average network throughput is obtained by deriving the mean success probability of the D2D links, whereas the spatial moments of the temporal mean AoI are obtained by deriving the moments of the temporal means of both success and scheduling probabilities of the status update links.

cs.IT↗

arXiv2021

Random Feature Attention

Transformers are state-of-the-art models for a variety of sequence modeling tasks. At their core is an attention function which models pairwise interactions between the inputs at every timestep. While attention is powerful, it does not scale efficiently to long sequences due to its quadratic time and space complexity in the sequence length. We propose RFA, a linear time and space attention that uses random feature methods to approximate the softmax function, and explore its application in transformers. RFA can be used as a drop-in replacement for conventional softmax attention and offers a straightforward way of learning with recency bias through an optional gating mechanism. Experiments on language modeling and machine translation demonstrate that RFA achieves similar or better performance compared to strong transformer baselines. In the machine translation experiment, RFA decodes twice as fast as a vanilla transformer. Compared to existing efficient transformer variants, RFA is competitive in terms of both accuracy and efficiency on three long text classification datasets. Our analysis shows that RFA's efficiency gains are especially notable on long sequences, suggesting that RFA will be particularly useful in tasks that require working with large inputs, fast decoding speed, or low memory footprints.

cs.CL↗

arXiv2021

Semantics-Empowered Communication for Networked Intelligent Systems

Wireless connectivity has traditionally been regarded as an opaque data pipe carrying messages, whose context-dependent meaning and effectiveness have been ignored. Nevertheless, in emerging cyber-physical and autonomous networked systems, acquiring, processing, and sending excessive amounts of distributed real-time data, which ends up being stale or useless to the end user, will cause communication bottlenecks, increased latency, and safety issues. We envision a communication paradigm shift, which makes the Semantics of Information, i.e., the significance and the usefulness of messages with respect to the goal of data exchange, the underpinning of the entire communication process. This entails a goal-oriented unification of information generation, transmission, and usage, by taking into account process dynamics, signal sparsity, data correlation, and semantic information attributes. We apply this structurally new, synergetic approach to a communication scenario where the destination is tasked with real-time source reconstruction for the purpose of remote actuation. Capitalizing on semantics-empowered sampling and communication policies, we show significant reduction in both reconstruction error and cost of actuation error, as well as in the number of uninformative samples generated.

cs.IT↗

arXiv2021

Optimizing Information Freshness in a Multiple Access Channel with Heterogeneous Devices

In this work, we study age-optimal scheduling with stability constraints in a multiple access channel with two heterogeneous source nodes transmitting to a common destination. The first node is connected to a power grid and it has randomly arriving data packets. Another energy harvesting (EH) sensor monitors a stochastic process and sends status updates to the destination. We formulate an optimization problem that aims at minimizing the average age of information (AoI) of the EH node subject to the queue stability condition of the grid-connected node. First, we consider a Probabilistic Random Access (PRA) policy where both nodes make independent transmission decisions based on some fixed probability distributions. We show that with this policy, the average AoI is equal to the average peak AoI, if the EH node only sends freshly generated samples. In addition, we derive the optimal solution in closed form, which reveals some interesting properties of the considered system. Furthermore, we consider a Drift-Plus-Penalty (DPP) policy and develop AoI-optimal and peak-AoI-optimal scheduling algorithms using the Lyapunov optimization theory. Simulation results show that the DPP policy outperforms the PRA policy in various scenarios, especially when the destination node has low multi-packet reception capabilities.

cs.IT↗

arXiv2021

Power Minimization for Age of Information Constrained Dynamic Control in Wireless Sensor Networks

We consider a system where multiple sensors communicate timely information about various random processes to a sink. The sensors share orthogonal sub-channels to transmit such information in the form of status update packets. A central controller can control the sampling actions of the sensors to trade-off between the transmit power consumption and information freshness which is quantified by the Age of Information (AoI). We jointly optimize the sampling action of each sensor, the transmit power allocation, and the sub-channel assignment to minimize the average total transmit power of all sensors subject to a maximum average AoI constraint for each sensor. To solve the problem, we develop a dynamic control algorithm using the Lyapunov drift-plus-penalty method and provide optimality analysis of the algorithm. According to the Lyapunov drift-plus-penalty method, to solve the main problem we need to solve an optimization problem in each time slot which is a mixed integer non-convex optimization problem. We propose a low-complexity sub-optimal solution for this per-slot optimization problem that provides near-optimal performance and we evaluate the computational complexity of the solution. Numerical results illustrate the performance of the proposed dynamic control algorithm and the performance of the sub-optimal solution for the per-slot optimization problems versus the different parameters of the system. The results show that the proposed dynamic control algorithm achieves more than $60~\%$ saving in the average total transmit power compared to a baseline policy.

cs.IT↗

arXiv2021

Robot Trajectory Planning With QoS Constrained IRS-assisted Millimeter-Wave Communications

This paper considers the joint optimization of trajectory and beamforming of a wirelessly connected robot using intelligent reflective surface (IRS)-assisted millimeter-wave (mm-wave) communications. The goal is to minimize the motion energy consumption subject to time and communication quality of service (QoS) constraints. This is a fundamental problem for industry 4.0, where robots may have to maximize their battery autonomy and communication efficiency. In such scenarios, IRSs and mm-waves can dramatically increase the spectrum efficiency of wireless communications providing high data rates and reliability for new industrial applications. We present a solution to the optimization problem that exploits mm-wave channel characteristics to decouple beamforming and trajectory optimizations. Then, the latter is solved by a successive-convex optimization (SCO) algorithm. The algorithm takes into account the obstacles' positions and a radio map and provides solutions that avoid collisions and satisfy the QoS constraint. Moreover, we prove that the algorithm converges to a solution satisfying the Karush-Kuhn-Tucker (KKT) conditions.

cs.NI↗

arXiv2020

Autonomous Maintenance in IoT Networks via AoI-driven Deep Reinforcement Learning

Internet of Things (IoT) with its growing number of deployed devices and applications raises significant challenges for network maintenance procedures. In this work, we formulate a problem of autonomous maintenance in IoT networks as a Partially Observable Markov Decision Process. Subsequently, we utilize Deep Reinforcement Learning algorithms (DRL) to train agents that decide if a maintenance procedure is in order or not and, in the former case, the proper type of maintenance needed. To avoid wasting the scarce resources of IoT networks we utilize the Age of Information (AoI) metric as a reward signal for the training of the smart agents. AoI captures the freshness of the sensory data which are transmitted by the IoT sensors as part of their normal service provision. Numerical results indicate that AoI integrates enough information about the past and present states of the system to be successfully used in the training of smart agents for the autonomous maintenance of the network.

cs.NI↗