Pub Date : 2023-12-22DOI: 10.1109/JSAIT.2023.3344760
Chris Ferguson;Leonard Kleinrock
In this paper we examine the general problem of determining when to update information that can go out-of-date. Not updating frequently enough results in poor decision making based on stale information. Updating too often results in excessive update costs. We study the tradeoff between having stale information and the cost of updating that information. We use a general model, some versions of which match an idealized version of the Age of Information (AoI) model. We first present the assumptions, and a novel methodology for solving problems of this sort. Then we solve the case where the update cost is fixed and the time-value of the information is well understood. Our results provide simple and powerful insights regarding optimal update times. We further look at cases where there are delays associated with sending a request for an update and receiving the update, cases where the update source may be stale, cases where the information cannot be used during the update process, and cases where update costs can change randomly.
{"title":"Optimal Update Times for Stale Information Metrics Including the Age of Information","authors":"Chris Ferguson;Leonard Kleinrock","doi":"10.1109/JSAIT.2023.3344760","DOIUrl":"https://doi.org/10.1109/JSAIT.2023.3344760","url":null,"abstract":"In this paper we examine the general problem of determining when to update information that can go out-of-date. Not updating frequently enough results in poor decision making based on stale information. Updating too often results in excessive update costs. We study the tradeoff between having stale information and the cost of updating that information. We use a general model, some versions of which match an idealized version of the Age of Information (AoI) model. We first present the assumptions, and a novel methodology for solving problems of this sort. Then we solve the case where the update cost is fixed and the time-value of the information is well understood. Our results provide simple and powerful insights regarding optimal update times. We further look at cases where there are delays associated with sending a request for an update and receiving the update, cases where the update source may be stale, cases where the information cannot be used during the update process, and cases where update costs can change randomly.","PeriodicalId":73295,"journal":{"name":"IEEE journal on selected areas in information theory","volume":"4 ","pages":"734-746"},"PeriodicalIF":0.0,"publicationDate":"2023-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10371395","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139060086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-20DOI: 10.1109/JSAIT.2023.3342569
Song Wei;Yao Xie;Christopher S. Josef;Rishikesan Kamaleswaran
We present a generalized linear structural causal model, coupled with a novel data-adaptive linear regularization, to recover causal directed acyclic graphs (DAGs) from time series. By leveraging a recently developed stochastic monotone Variational Inequality (VI) formulation, we cast the causal discovery problem as a general convex optimization. Furthermore, we develop a non-asymptotic recovery guarantee and quantifiable uncertainty by solving a linear program to establish confidence intervals for a wide range of non-linear monotone link functions. We validate our theoretical results and show the competitive performance of our method via extensive numerical experiments. Most importantly, we demonstrate the effectiveness of our approach in recovering highly interpretable causal DAGs over Sepsis Associated Derangements (SADs) while achieving comparable prediction performance to powerful “black-box” models such as XGBoost.
我们提出了一种广义线性结构因果模型，并结合新颖的数据适应性线性正则化，从时间序列中恢复因果有向无环图（DAG）。通过利用最近开发的随机单调变式不等式（VI）公式，我们将因果发现问题视为一般凸优化问题。此外，我们还通过求解线性程序，为各种非线性单调联系函数建立置信区间，从而开发出一种非渐近恢复保证和可量化的不确定性。我们通过大量数值实验验证了我们的理论结果，并展示了我们的方法具有竞争力的性能。最重要的是，我们证明了我们的方法在恢复败血症相关变异 (SAD) 的高度可解释因果 DAG 方面的有效性，同时实现了与 XGBoost 等强大 "黑盒 "模型相当的预测性能。
{"title":"Causal Graph Discovery From Self and Mutually Exciting Time Series","authors":"Song Wei;Yao Xie;Christopher S. Josef;Rishikesan Kamaleswaran","doi":"10.1109/JSAIT.2023.3342569","DOIUrl":"https://doi.org/10.1109/JSAIT.2023.3342569","url":null,"abstract":"We present a generalized linear structural causal model, coupled with a novel data-adaptive linear regularization, to recover causal directed acyclic graphs (DAGs) from time series. By leveraging a recently developed stochastic monotone Variational Inequality (VI) formulation, we cast the causal discovery problem as a general convex optimization. Furthermore, we develop a non-asymptotic recovery guarantee and quantifiable uncertainty by solving a linear program to establish confidence intervals for a wide range of non-linear monotone link functions. We validate our theoretical results and show the competitive performance of our method via extensive numerical experiments. Most importantly, we demonstrate the effectiveness of our approach in recovering highly interpretable causal DAGs over Sepsis Associated Derangements (SADs) while achieving comparable prediction performance to powerful “black-box” models such as XGBoost.","PeriodicalId":73295,"journal":{"name":"IEEE journal on selected areas in information theory","volume":"4 ","pages":"747-761"},"PeriodicalIF":0.0,"publicationDate":"2023-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139090401","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-19DOI: 10.1109/JSAIT.2023.3344586
Siqi Meng;Shaohua Wu;Aimin Li;Qinyu Zhang
In the past decade, the emergence of beyond fifth generation (B5G) wireless networks has necessitated the timely updating of system states in Internet of Things (IoT) and cyber-physical systems, where Age of Information (AoI) has been a well-concentrated metric. However, the content-agnostic nature of AoI reflects its limitation of characterizing the significance of status update messages, which induces various variants for AoI including Age of Incorrect Information (AoII). AoII is a goal-oriented significance (etymological meaning of “semantics”) metric that could overcome such shortcomings, and thus analyzing AoII performance can be a potential approach of realizing semantic communications. Nevertheless, AoII analysis of practical coded status update system under finite blocklength (FBL) regime is still in its nascent stages. To the best of our knowledge, our study represents the first analysis of AoII for FBL regime. We explicitly obtain the average AoII expressions for different transmission schemes including Automatic Repeat reQuest (ARQ), Hybrid ARQ (HARQ), and non-ARQ transmission schemes. Moreover, we theoretically prove that non-ARQ scheme outperforms ARQ schemes in terms of AoII, and numerically compare AoII performance between non-ARQ and HARQ schemes by formulating and solving the AoII-optimal block assignment problem. Extensive simulation results show the superiority of AoII-optimal transmission schemes.
{"title":"Toward Goal-Oriented Semantic Communications: AoII Analysis of Coded Status Update System Under FBL Regime","authors":"Siqi Meng;Shaohua Wu;Aimin Li;Qinyu Zhang","doi":"10.1109/JSAIT.2023.3344586","DOIUrl":"https://doi.org/10.1109/JSAIT.2023.3344586","url":null,"abstract":"In the past decade, the emergence of beyond fifth generation (B5G) wireless networks has necessitated the timely updating of system states in Internet of Things (IoT) and cyber-physical systems, where Age of Information (AoI) has been a well-concentrated metric. However, the content-agnostic nature of AoI reflects its limitation of characterizing the significance of status update messages, which induces various variants for AoI including Age of Incorrect Information (AoII). AoII is a goal-oriented significance (etymological meaning of “semantics”) metric that could overcome such shortcomings, and thus analyzing AoII performance can be a potential approach of realizing semantic communications. Nevertheless, AoII analysis of practical coded status update system under finite blocklength (FBL) regime is still in its nascent stages. To the best of our knowledge, our study represents the first analysis of AoII for FBL regime. We explicitly obtain the average AoII expressions for different transmission schemes including Automatic Repeat reQuest (ARQ), Hybrid ARQ (HARQ), and non-ARQ transmission schemes. Moreover, we theoretically prove that non-ARQ scheme outperforms ARQ schemes in terms of AoII, and numerically compare AoII performance between non-ARQ and HARQ schemes by formulating and solving the AoII-optimal block assignment problem. Extensive simulation results show the superiority of AoII-optimal transmission schemes.","PeriodicalId":73295,"journal":{"name":"IEEE journal on selected areas in information theory","volume":"4 ","pages":"718-733"},"PeriodicalIF":0.0,"publicationDate":"2023-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139050591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A digital twin (DT) leverages a virtual representation of the physical world, along with communication (e.g., 6G), computing (e.g., edge computing), and artificial intelligence (AI) technologies to enable many connected intelligence services. In order to handle the large amounts of network data based on digital twins (DTs), wireless systems can exploit the paradigm of semantic communication (SC) for facilitating informed decision-making under strict communication constraints by utilizing AI techniques such as causal reasoning. In this paper, a novel framework called causal semantic communication (CSC) is proposed for DT-based wireless systems. The CSC system is posed as an imitation learning (IL) problem, where the transmitter, with access to optimal network control policies using a DT, teaches the receiver using SC over a bandwidth-limited wireless channel how to improve its knowledge to perform optimal control actions. The causal structure in the transmitter’s data is extracted using novel approaches from the framework of deep end-to-end causal inference, thereby enabling the creation of a semantic representation that is causally invariant, which in turn helps generalize the learned knowledge of the system to new and unseen situations. The CSC decoder at the receiver is designed to extract and estimate semantic information while ensuring high semantic reliability. The receiver control policies, semantic decoder, and causal inference are formulated as a bi-level optimization problem within a variational inference framework. This problem is solved using a novel concept called network state models, inspired from world models in generative AI, that faithfully represents the environment dynamics leading to data generation. Furthermore, the proposed framework includes an analytical characterization of the performance gap that results from employing a suboptimal policy learned by the receiver that uses the transmitted semantic information to construct a model of the physical environment. The CSC system utilizes two concepts, namely the integrated information theory principle in the theory of consciousness and the abstract cell complex concept in topology, to precisely express the information content conveyed by the causal states and their relationships. Through this analysis, novel formulations of semantic information, semantic reliability, distortion, and similarity metrics are proposed, which extend beyond Shannon’s concept of uncertainty. Simulation results demonstrate that the proposed CSC system outperforms conventional wireless and state-of-the-art SC systems by achieving better semantic reliability with reduced bits and enabling better control policies over time thanks to the generative AI architecture.
{"title":"Causal Semantic Communication for Digital Twins: A Generalizable Imitation Learning Approach","authors":"Christo Kurisummoottil Thomas;Walid Saad;Yong Xiao","doi":"10.1109/JSAIT.2023.3336538","DOIUrl":"https://doi.org/10.1109/JSAIT.2023.3336538","url":null,"abstract":"A digital twin (DT) leverages a virtual representation of the physical world, along with communication (e.g., 6G), computing (e.g., edge computing), and artificial intelligence (AI) technologies to enable many connected intelligence services. In order to handle the large amounts of network data based on digital twins (DTs), wireless systems can exploit the paradigm of semantic communication (SC) for facilitating informed decision-making under strict communication constraints by utilizing AI techniques such as causal reasoning. In this paper, a novel framework called causal semantic communication (CSC) is proposed for DT-based wireless systems. The CSC system is posed as an imitation learning (IL) problem, where the transmitter, with access to optimal network control policies using a DT, teaches the receiver using SC over a bandwidth-limited wireless channel how to improve its knowledge to perform optimal control actions. The causal structure in the transmitter’s data is extracted using novel approaches from the framework of deep end-to-end causal inference, thereby enabling the creation of a semantic representation that is causally invariant, which in turn helps generalize the learned knowledge of the system to new and unseen situations. The CSC decoder at the receiver is designed to extract and estimate semantic information while ensuring high semantic reliability. The receiver control policies, semantic decoder, and causal inference are formulated as a bi-level optimization problem within a variational inference framework. This problem is solved using a novel concept called network state models, inspired from world models in generative AI, that faithfully represents the environment dynamics leading to data generation. Furthermore, the proposed framework includes an analytical characterization of the performance gap that results from employing a suboptimal policy learned by the receiver that uses the transmitted semantic information to construct a model of the physical environment. The CSC system utilizes two concepts, namely the integrated information theory principle in the theory of consciousness and the abstract cell complex concept in topology, to precisely express the information content conveyed by the causal states and their relationships. Through this analysis, novel formulations of semantic information, semantic reliability, distortion, and similarity metrics are proposed, which extend beyond Shannon’s concept of uncertainty. Simulation results demonstrate that the proposed CSC system outperforms conventional wireless and state-of-the-art SC systems by achieving better semantic reliability with reduced bits and enabling better control policies over time thanks to the generative AI architecture.","PeriodicalId":73295,"journal":{"name":"IEEE journal on selected areas in information theory","volume":"4 ","pages":"698-717"},"PeriodicalIF":0.0,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138822192","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-30DOI: 10.1109/JSAIT.2023.3337203
Ali Maatouk;Mohamad Assaad;Anthony Ephremides
In this paper, we analyze status update systems modeled through the Stochastic Hybrid Systems (SHSs) tool. Contrary to previous works, we allow the system’s transition dynamics to be polynomial functions of the Age of Information (AoI). This dependence allows us to encapsulate many applications and opens the door for more sophisticated systems to be studied. However, this same dependence on the AoI engenders technical and analytical difficulties that we address in this paper. Specifically, we first showcase several characteristics of the age processes modeled through the SHSs tool. Then, we provide a framework to establish the Lagrange stability and positive recurrence of these processes. Building on this, we provide an approach to compute the $m$ -th moment of the age processes. Interestingly, this technique allows us to approximate the average age by solving a simple set of linear equations. Equipped with this approach, we also provide a sequential convex approximation method to optimize the average age by calibrating the parameters of the system. Finally, we consider an age-dependent CSMA environment where the back-off duration depends on the instantaneous age. By leveraging our analysis, we contrast its performance to the age-blind CSMA and showcase the age performance gain provided by the former.
{"title":"Age-Aware Stochastic Hybrid Systems: Stability, Solutions, and Applications","authors":"Ali Maatouk;Mohamad Assaad;Anthony Ephremides","doi":"10.1109/JSAIT.2023.3337203","DOIUrl":"https://doi.org/10.1109/JSAIT.2023.3337203","url":null,"abstract":"In this paper, we analyze status update systems modeled through the Stochastic Hybrid Systems (SHSs) tool. Contrary to previous works, we allow the system’s transition dynamics to be polynomial functions of the Age of Information (AoI). This dependence allows us to encapsulate many applications and opens the door for more sophisticated systems to be studied. However, this same dependence on the AoI engenders technical and analytical difficulties that we address in this paper. Specifically, we first showcase several characteristics of the age processes modeled through the SHSs tool. Then, we provide a framework to establish the Lagrange stability and positive recurrence of these processes. Building on this, we provide an approach to compute the \u0000<inline-formula> <tex-math>$m$ </tex-math></inline-formula>\u0000-th moment of the age processes. Interestingly, this technique allows us to approximate the average age by solving a simple set of linear equations. Equipped with this approach, we also provide a sequential convex approximation method to optimize the average age by calibrating the parameters of the system. Finally, we consider an age-dependent CSMA environment where the back-off duration depends on the instantaneous age. By leveraging our analysis, we contrast its performance to the age-blind CSMA and showcase the age performance gain provided by the former.","PeriodicalId":73295,"journal":{"name":"IEEE journal on selected areas in information theory","volume":"4 ","pages":"762-783"},"PeriodicalIF":0.0,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139434818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-20DOI: 10.1109/JSAIT.2023.3334692
Shubham Aggarwal;Muhammad Aneeq uz Zaman;Melih Bastopcu;Tamer Başar
In this paper, we study a multi-agent game between $N$ agents, which solve a consensus problem, and receive state information through a wireless network, that is controlled by a Base station (BS). Due to a hard-bandwidth constraint, the BS can concurrently connect at most $R_{d} < N$ agents over the network. This causes an intermittency in the agents’ state information, necessitating state estimation based on each agent’s information history. Under standard assumptions on the information structure, we separate each agent’s estimation and control problems. The BS aims to find the optimum scheduling policy that minimizes a weighted age of information based performance metric, subject to the hard-bandwidth constraint. We first relax the hard constraint to a soft update-rate constraint and compute an optimal policy for the relaxed problem by reformulating it into an MDP. This then inspires a sub-optimal policy for the bandwidth constrained problem, which is shown to approach the optimal policy as $N rightarrow infty $ . Next, we solve the consensus problem using the mean-field game framework. By explicitly constructing the mean-field system, we prove the existence of a unique mean-field equilibrium. Consequently, we show that the equilibrium policies obtained constitute an $epsilon $ –Nash equilibrium for the finite-agent system.
{"title":"Weighted Age of Information-Based Scheduling for Large Population Games on Networks","authors":"Shubham Aggarwal;Muhammad Aneeq uz Zaman;Melih Bastopcu;Tamer Başar","doi":"10.1109/JSAIT.2023.3334692","DOIUrl":"https://doi.org/10.1109/JSAIT.2023.3334692","url":null,"abstract":"In this paper, we study a multi-agent game between \u0000<inline-formula> <tex-math>$N$ </tex-math></inline-formula>\u0000 agents, which solve a consensus problem, and receive state information through a wireless network, that is controlled by a Base station (BS). Due to a hard-bandwidth constraint, the BS can concurrently connect at most \u0000<inline-formula> <tex-math>$R_{d} < N$ </tex-math></inline-formula>\u0000 agents over the network. This causes an intermittency in the agents’ state information, necessitating state estimation based on each agent’s information history. Under standard assumptions on the information structure, we separate each agent’s estimation and control problems. The BS aims to find the optimum scheduling policy that minimizes a weighted age of information based performance metric, subject to the hard-bandwidth constraint. We first relax the hard constraint to a soft update-rate constraint and compute an optimal policy for the relaxed problem by reformulating it into an MDP. This then inspires a sub-optimal policy for the bandwidth constrained problem, which is shown to approach the optimal policy as \u0000<inline-formula> <tex-math>$N rightarrow infty $ </tex-math></inline-formula>\u0000. Next, we solve the consensus problem using the mean-field game framework. By explicitly constructing the mean-field system, we prove the existence of a unique mean-field equilibrium. Consequently, we show that the equilibrium policies obtained constitute an \u0000<inline-formula> <tex-math>$epsilon $ </tex-math></inline-formula>\u0000–Nash equilibrium for the finite-agent system.","PeriodicalId":73295,"journal":{"name":"IEEE journal on selected areas in information theory","volume":"4 ","pages":"682-697"},"PeriodicalIF":0.0,"publicationDate":"2023-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138678678","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-09DOI: 10.1109/JSAIT.2023.3329121
Giuseppe Cocco;Andrea Munari;Gianluigi Liva
We study a system in which two-state Markov sources send status updates to a common receiver over a slotted ALOHA random access channel. We characterize the performance of the system in terms of state estimation entropy (SEE), which measures the uncertainty at the receiver about the sources’ state. Two channel access strategies are considered: a reactive policy that depends on the source behaviour and a random one that is independent of it. We prove that the considered policies can be studied using two different hidden Markov models and show through a density evolution analysis that the reactive strategy outperforms the random one in terms of SEE while the opposite is true for age of information. Furthermore, we characterize the probability of error in the state estimation at the receiver, considering a maximum a posteriori and a low-complexity (decode & hold) estimator. Our study provides useful insights on the design trade-offs that emerge when different performance metrics are adopted. Moreover, we show how the source statistics significantly impact the system performance.
我们研究了一个系统，在这个系统中，双状态马尔可夫信号源通过插槽式 ALOHA 随机接入信道向一个共同接收器发送状态更新。我们用状态估计熵（SEE）来描述系统的性能，该熵衡量接收方对信源状态的不确定性。我们考虑了两种信道接入策略：一种是取决于信源行为的反应策略，另一种是与信源行为无关的随机策略。我们证明可以使用两种不同的隐马尔可夫模型来研究所考虑的策略，并通过密度演化分析表明，就 SEE 而言，反应策略优于随机策略，而信息年龄则相反。此外，考虑到最大后验和低复杂度（解码与保持）估计器，我们还描述了接收器状态估计的错误概率。我们的研究为采用不同性能指标时出现的设计权衡提供了有用的见解。此外，我们还展示了信号源统计如何对系统性能产生重大影响。
{"title":"Remote Monitoring of Two-State Markov Sources via Random Access Channels: An Information Freshness vs. State Estimation Entropy Perspective","authors":"Giuseppe Cocco;Andrea Munari;Gianluigi Liva","doi":"10.1109/JSAIT.2023.3329121","DOIUrl":"10.1109/JSAIT.2023.3329121","url":null,"abstract":"We study a system in which two-state Markov sources send status updates to a common receiver over a slotted ALOHA random access channel. We characterize the performance of the system in terms of state estimation entropy (SEE), which measures the uncertainty at the receiver about the sources’ state. Two channel access strategies are considered: a reactive policy that depends on the source behaviour and a random one that is independent of it. We prove that the considered policies can be studied using two different hidden Markov models and show through a density evolution analysis that the reactive strategy outperforms the random one in terms of SEE while the opposite is true for age of information. Furthermore, we characterize the probability of error in the state estimation at the receiver, considering a maximum a posteriori and a low-complexity (decode & hold) estimator. Our study provides useful insights on the design trade-offs that emerge when different performance metrics are adopted. Moreover, we show how the source statistics significantly impact the system performance.","PeriodicalId":73295,"journal":{"name":"IEEE journal on selected areas in information theory","volume":"4 ","pages":"651-666"},"PeriodicalIF":0.0,"publicationDate":"2023-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135560847","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Intelligent real-time applications, such as video surveillance, demand intensive computation to extract status information from raw sensing data. This poses a substantial challenge in orchestrating computation and communication resources to provide fresh status information. In this paper, we consider a scenario where multiple energy-constrained devices served by an edge server. To extract status information, each device can either do the computation locally or offload it to the edge server. A scheduling policy is needed to determine when and where to compute for each device, taking into account communication and computation capabilities, as well as task-specific timeliness requirements. To that end, we first model the timeliness requirements as general penalty functions of Age of Information (AoI). A convex optimization problem is formulated to provide a lower bound of the minimum AoI penalty given system parameters. Using KKT conditions, we proposed a novel scheduling policy which evaluates status update priorities based on communication and computation delays and task-specific timeliness requirements. The proposed policy is applied to an object tracking application and carried out on a large video dataset. Simulation results show that our policy improves tracking accuracy compared with scheduling policies based on video content information.
{"title":"Optimizing Task-Specific Timeliness With Edge-Assisted Scheduling for Status Update","authors":"Jingzhou Sun;Lehan Wang;Zhaojun Nan;Yuxuan Sun;Sheng Zhou;Zhisheng Niu","doi":"10.1109/JSAIT.2023.3329017","DOIUrl":"10.1109/JSAIT.2023.3329017","url":null,"abstract":"Intelligent real-time applications, such as video surveillance, demand intensive computation to extract status information from raw sensing data. This poses a substantial challenge in orchestrating computation and communication resources to provide fresh status information. In this paper, we consider a scenario where multiple energy-constrained devices served by an edge server. To extract status information, each device can either do the computation locally or offload it to the edge server. A scheduling policy is needed to determine when and where to compute for each device, taking into account communication and computation capabilities, as well as task-specific timeliness requirements. To that end, we first model the timeliness requirements as general penalty functions of Age of Information (AoI). A convex optimization problem is formulated to provide a lower bound of the minimum AoI penalty given system parameters. Using KKT conditions, we proposed a novel scheduling policy which evaluates status update priorities based on communication and computation delays and task-specific timeliness requirements. The proposed policy is applied to an object tracking application and carried out on a large video dataset. Simulation results show that our policy improves tracking accuracy compared with scheduling policies based on video content information.","PeriodicalId":73295,"journal":{"name":"IEEE journal on selected areas in information theory","volume":"4 ","pages":"624-638"},"PeriodicalIF":0.0,"publicationDate":"2023-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134981772","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-02DOI: 10.1109/JSAIT.2023.3328651
Kang Du;Yu Xiang
It has become increasingly common nowadays to collect observations of feature and response pairs from different environments. As a consequence, one has to apply learned predictors to data with a different distribution due to distribution shifts. One principled approach is to adopt the structural causal models to describe training and test models, following the invariance principle which says that the conditional distribution of the response given its predictors remains the same across environments. However, this principle might be violated in practical settings when the response is intervened. A natural question is whether it is still possible to identify other forms of invariance to facilitate prediction in unseen environments. To shed light on this challenging scenario, we focus on linear structural causal models (SCMs) and introduce invariant matching property (IMP), an explicit relation to capture interventions through an additional feature, leading to an alternative form of invariance that enables a unified treatment of general interventions on the response as well as the predictors. We analyze the asymptotic generalization errors of our method under both the discrete and continuous environment settings, where the continuous case is handled by relating it to the semiparametric varying coefficient models. We present algorithms that show competitive performance compared to existing methods over various experimental settings including a COVID dataset.
{"title":"Learning Invariant Representations Under General Interventions on the Response","authors":"Kang Du;Yu Xiang","doi":"10.1109/JSAIT.2023.3328651","DOIUrl":"10.1109/JSAIT.2023.3328651","url":null,"abstract":"It has become increasingly common nowadays to collect observations of feature and response pairs from different environments. As a consequence, one has to apply learned predictors to data with a different distribution due to distribution shifts. One principled approach is to adopt the structural causal models to describe training and test models, following the invariance principle which says that the conditional distribution of the response given its predictors remains the same across environments. However, this principle might be violated in practical settings when the response is intervened. A natural question is whether it is still possible to identify other forms of invariance to facilitate prediction in unseen environments. To shed light on this challenging scenario, we focus on linear structural causal models (SCMs) and introduce invariant matching property (IMP), an explicit relation to capture interventions through an additional feature, leading to an alternative form of invariance that enables a unified treatment of general interventions on the response as well as the predictors. We analyze the asymptotic generalization errors of our method under both the discrete and continuous environment settings, where the continuous case is handled by relating it to the semiparametric varying coefficient models. We present algorithms that show competitive performance compared to existing methods over various experimental settings including a COVID dataset.","PeriodicalId":73295,"journal":{"name":"IEEE journal on selected areas in information theory","volume":"4 ","pages":"808-819"},"PeriodicalIF":0.0,"publicationDate":"2023-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134887604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-01DOI: 10.1109/JSAIT.2023.3329431
Karim Banawan;Ahmed Arafa;Karim G. Seddik
We consider a multi-process remote estimation system observing $K$ independent Ornstein-Uhlenbeck processes. In this system, a shared sensor samples the $K$ processes in such a way that the long-term average sum mean square error (MSE) is minimized using signal-independent sampling policies, in which sampling instances are chosen independently from the processes’ values. The sensor operates under a total sampling frequency constraint $f_{max }$ . The samples from all processes consume random processing delays in a shared queue and then are transmitted over an erasure channel with probability $epsilon $ . We study two variants of the problem: first, when the samples are scheduled according to a Maximum-Age-First (MAF) policy, and the receiver provides an erasure status feedback; and second, when samples are scheduled according to a Round-Robin (RR) policy, when there is no erasure status feedback from the receiver. Aided by optimal structural results, we show that the optimal sampling policy for both settings, under some conditions, is a threshold policy. We characterize the optimal threshold and the corresponding optimal long-term average sum MSE as a function of $K$ , $f_{max }$ , $epsilon $ , and the statistical properties of the observed processes. Our results show that, with an exponentially distributed service rate, the optimal threshold $tau ^{ast}$ increases as the number of processes $K$ increases, for both settings. Additionally, we show that the optimal threshold is an increasing function of $epsilon $ in the case of available erasure status feedback, while it exhibits the opposite behavior, i.e., $tau ^{ast}$ is a decreasing function of $epsilon $ , in the case of absent erasure status feedback.
我们考虑了一个观察K个独立的Ornstein-Uhlenbeck过程的多过程远程估计系统。在该系统中，共享传感器以这样一种方式对K个过程进行采样，即使用与信号无关的采样策略最小化长期平均和均方误差(MSE)，其中采样实例的选择独立于过程的值。传感器在总采样频率约束下工作。来自所有进程的采样在共享队列中消耗随机处理延迟，然后以概率通过擦除通道传输。我们研究了该问题的两种变体:第一，当样本按照最大年龄优先(maximum - age first, MAF)策略进行调度时，接收方提供擦除状态反馈;第二种情况是，当采样按RR (Round-Robin)策略调度时，当接收方没有擦除状态反馈时。在最优结构结果的帮助下，我们证明了在某些条件下，两种设置的最优抽样策略是阈值策略。我们将最佳阈值和相应的最佳长期平均和MSE描述为K, f和观察过程的统计特性的函数。结果表明，在服务率呈指数分布的情况下，对于两种设置，最优阈值τ*都随着进程数K的增加而增加。此外，我们证明了在可用的擦除状态反馈情况下，最优阈值是一个增加函数，而在没有擦除状态反馈的情况下，它表现出相反的行为，即τ*是一个减小函数。
{"title":"Timely Multi-Process Estimation Over Erasure Channels With and Without Feedback: Signal-Independent Policies","authors":"Karim Banawan;Ahmed Arafa;Karim G. Seddik","doi":"10.1109/JSAIT.2023.3329431","DOIUrl":"10.1109/JSAIT.2023.3329431","url":null,"abstract":"We consider a multi-process remote estimation system observing \u0000<inline-formula> <tex-math>$K$ </tex-math></inline-formula>\u0000 independent Ornstein-Uhlenbeck processes. In this system, a shared sensor samples the \u0000<inline-formula> <tex-math>$K$ </tex-math></inline-formula>\u0000 processes in such a way that the long-term average sum mean square error (MSE) is minimized using signal-independent sampling policies, in which sampling instances are chosen independently from the processes’ values. The sensor operates under a total sampling frequency constraint \u0000<inline-formula> <tex-math>$f_{max }$ </tex-math></inline-formula>\u0000. The samples from all processes consume random processing delays in a shared queue and then are transmitted over an erasure channel with probability \u0000<inline-formula> <tex-math>$epsilon $ </tex-math></inline-formula>\u0000. We study two variants of the problem: first, when the samples are scheduled according to a Maximum-Age-First (MAF) policy, and the receiver provides an erasure status feedback; and second, when samples are scheduled according to a Round-Robin (RR) policy, when there is no erasure status feedback from the receiver. Aided by optimal structural results, we show that the optimal sampling policy for both settings, under some conditions, is a threshold policy. We characterize the optimal threshold and the corresponding optimal long-term average sum MSE as a function of \u0000<inline-formula> <tex-math>$K$ </tex-math></inline-formula>\u0000, \u0000<inline-formula> <tex-math>$f_{max }$ </tex-math></inline-formula>\u0000, \u0000<inline-formula> <tex-math>$epsilon $ </tex-math></inline-formula>\u0000, and the statistical properties of the observed processes. Our results show that, with an exponentially distributed service rate, the optimal threshold \u0000<inline-formula> <tex-math>$tau ^{ast}$ </tex-math></inline-formula>\u0000 increases as the number of processes \u0000<inline-formula> <tex-math>$K$ </tex-math></inline-formula>\u0000 increases, for both settings. Additionally, we show that the optimal threshold is an increasing function of \u0000<inline-formula> <tex-math>$epsilon $ </tex-math></inline-formula>\u0000 in the case of available erasure status feedback, while it exhibits the opposite behavior, i.e., \u0000<inline-formula> <tex-math>$tau ^{ast}$ </tex-math></inline-formula>\u0000 is a decreasing function of \u0000<inline-formula> <tex-math>$epsilon $ </tex-math></inline-formula>\u0000, in the case of absent erasure status feedback.","PeriodicalId":73295,"journal":{"name":"IEEE journal on selected areas in information theory","volume":"4 ","pages":"607-623"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135362790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：