2023 57th Annual Conference on Information Sciences and Systems (CISS)最新文献_第4页

Parallel and Serial Two-Sensor Distributed Detection Considering Binary Symmetric Channel 考虑二进制对称信道的并行和串行双传感器分布式检测

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089660

Xingjian Sun, Lei Cao, R. Viswanathan

引用次数: 0

An ALOHA multi-user game with tradeoff between throughput and transmission proportional fairness 在吞吐量和传输比例公平之间权衡的ALOHA多用户博弈

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089707

A. Garnaev, W. Trappe

{"title":"An ALOHA multi-user game with tradeoff between throughput and transmission proportional fairness","authors":"A. Garnaev, W. Trappe","doi":"10.1109/CISS56502.2023.10089707","DOIUrl":"https://doi.org/10.1109/CISS56502.2023.10089707","url":null,"abstract":"The paper considers an ALOHA type communication, where several users send data, and investigates the problem in a game-theoretic framework. We show that in such ALOHA type communication, the throughput metric leads to a continuum of equilibria. Moreover, its traditional extension via adding a transmission cost, which might collapse such a continuum to a finite number of equilibria, actually remains a multi equilibria situation, and that this might potentially destabilize users communication. Also we show that in contrast to the flat-fading multiple access communication (MAC) networks, in an ALOHA network, users' communication might not be stabilized via switching from throughput to latency communication utility. This phenomena puts forward a question of which metric might lead to a unique equilibrium, and thus to stability in multi user ALOHA type communication. Here for multi user ALOHA type communication we suggest an advanced communication metric reflecting tradeoff between throughput and the transmission's fairness. Such metric might be also interpreted as a trade-off for a user between its selfish and cooperative behavior. We prove that, in contrast to the throughput metric, such an advanced metric always lead to a unique equilibrium, and thus to communication stability under the corresponding transmission protocol. The other proven advantage is that it supports uninterrupted communication between the users. The equilibrium is derived in closed form. Finally, it is shown how to optimize weights of throughput and transmission's fairness in the suggested trade-off metric.","PeriodicalId":243775,"journal":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121571880","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}

引用次数: 0

Extended Abstract: Learning in Low-rank MDPs with Density Features 具有密度特征的低秩mdp的学习

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089731

Audrey Huang, Jinglin Chen, Nan Jiang

{"title":"Extended Abstract: Learning in Low-rank MDPs with Density Features","authors":"Audrey Huang, Jinglin Chen, Nan Jiang","doi":"10.1109/CISS56502.2023.10089731","DOIUrl":"https://doi.org/10.1109/CISS56502.2023.10089731","url":null,"abstract":"In online reinforcement learning (RL) with large state spaces, MDPs with low-rank transitions-that is, the transition matrix can be factored into the product of two matrices, left and right-is a highly representative structure that enables tractable exploration. When given to the learner, the left matrix enables expressive function approximation for value-based learning, and this setting has been studied extensively (e.g., in linear MDPs). Similarly, the right matrix induces powerful models for state-occupancy densities. However, using such density features to learn in low-rank MDPs has never been studied to the best of our knowledge, and is a setting with interesting connections to leveraging the power of generative models in RL. In this work, we initiate the study of learning low-rank MDPs with density features. Our algorithm performs reward-free learning and builds an exploratory distribution in a level-by-level manner. It uses the density features for off-policy estimation of the policies' state distributions, and constructs the exploratory data by choosing the barycentric spanner of these distributions. From an analytical point of view, the additive error of distribution estimation is largely incompatible with the multiplicative definition of data coverage (e.g., concentrability). In the absence of strong assumptions like reachability, this incompatibility may lead to exponential or even infinite errors under standard analysis strategies, which we overcome via novel technical tools.","PeriodicalId":243775,"journal":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125513882","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}

引用次数: 0

Development of multifunctional hyperspectral/near-infrared imaging camera system for intraoperative tissue characterization and assessment in vivo 用于术中组织表征和体内评估的多功能高光谱/近红外成像相机系统的开发

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089670

C. Lee, Anees A. Naik, Sailee Naik, Michele Saruwatari, Kochai Jawed, K. M. Ali, Bo Ning, R. J. Cha

引用次数: 0

Federated Learning With Server Learning for Non-IID Data 非iid数据的联邦学习与服务器学习

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089643

V. Mai, R. La, Tao Zhang, Yuxuan Huang, A. Battou

引用次数: 2

Toward Designing an Attentive Deep Trajectory Predictor Based on Bluetooth Low Energy Signal 基于蓝牙低能量信号的深度轨迹预测器设计

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089682

Weijia Lu, Xiaofeng Ma, Xiaodong Zhang, Zhifei Yang, Qinghua Wang, Chuang Liu, Tao Yang

引用次数: 0

Stopping Criteria for Compressive Sensing OFDM Channel Estimation using OMP 基于OMP的OFDM信道估计的停止准则

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089664

John Franklin, A. Cooper

引用次数: 0

Communication-Efficient Federated Learning with Channel-Aware Sparsification over Wireless Networks 无线网络中信道感知稀疏化的高效通信联邦学习

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089723

Richeng Jin, Philip Dai, Kaiqi Xiong

{"title":"Communication-Efficient Federated Learning with Channel-Aware Sparsification over Wireless Networks","authors":"Richeng Jin, Philip Dai, Kaiqi Xiong","doi":"10.1109/CISS56502.2023.10089723","DOIUrl":"https://doi.org/10.1109/CISS56502.2023.10089723","url":null,"abstract":"Federated learning (FL) has recently emerged as a popular distributed learning paradigm since it allows collaborative training of a global machine learning model while keeping the training data of its participating workers locally. This paradigm enables the model training to harness the computing power across the network of FL and preserves the privacy of local training data. However, communication efficiency has become one of the major concerns of FL due to frequent model updates through the network, especially for devices in wireless networks that have limited communication resources. Despite that various communication-efficient compression mechanisms (e.g., quantization and sparsification) have been incorporated into FL, most of the existing studies are only concerned with resource allocation optimization given predetermined compression mechanisms, and few of them take wireless communication into consideration in the design of the compression mechanisms. In this paper, we study the impact of sparsification and wireless channels on FL performance. Specifically, we propose a channel-aware sparsification mechanism and derive a closed-form solution for communication time allocation for workers in a TDMA setting. Extensive simulations are conducted to validate the effectiveness of the proposed mechanism.","PeriodicalId":243775,"journal":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123795982","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}

引用次数: 0

Outlier Detection for Generative Models with Performance Guarantees 性能保证生成模型的离群点检测

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089758

Jin-wu Gao, Jirong Yi, Weiyu Xu

引用次数: 0

Interpretable Skill Learning for Dynamic Treatment Regimes through Imitation 通过模仿动态治疗机制的可解释技能学习

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089648

Yushan Jiang, Wenchao Yu, Dongjin Song, Wei Cheng, Haifeng Chen

{"title":"Interpretable Skill Learning for Dynamic Treatment Regimes through Imitation","authors":"Yushan Jiang, Wenchao Yu, Dongjin Song, Wei Cheng, Haifeng Chen","doi":"10.1109/CISS56502.2023.10089648","DOIUrl":"https://doi.org/10.1109/CISS56502.2023.10089648","url":null,"abstract":"Imitation learning that mimics experts' skills from their demonstrations has shown great success in discovering dynamic treatment regimes, i.e., the optimal decision rules to treat an individual patient based on related evolving treatment and covariate history. Existing imitation learning methods, however, still lack the capability to interpret the underlying rationales of the learned policy in a faithful way. Moreover, since dynamic treatment regimes for patients often exhibit varying patterns, i.e., symptoms that transit from one to another, the flat policy learned by a vanilla imitation learning method is typically undesired. To this end, we propose an Interpretable Skill Learning (ISL) framework to resolve the aforementioned challenges for dynamic treatment regimes through imitation. The key idea is to model each segment of experts' demonstrations with a prototype layer and integrate it with the imitation learning layer to enhance the interpretation capability. On one hand, the ISL framework is able to provide interpretable explanations by matching the prototype to exemplar segments during the inference stage, which enables doctors to perform reasoning of the learned demonstrations based on human-understandable patient symptoms and lab results. On the other hand, the obtained skill embedding consisting of prototypes serves as conditional information to the imitation learning layer, which implicitly guides the policy network to provide a more accurate demonstration when the patients' state switches from one stage to another. Thoroughly empirical studies demonstrate that our proposed ISL technique can achieve better performance than state-of-the-art methods. Moreover, the proposed ISL framework also exhibits good interpretability which cannot be observed in existing methods.","PeriodicalId":243775,"journal":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128779750","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}

引用次数: 0