{"title":"Estimating Sparse Covariance Matrix Under Differential Privacy via Thresholding","authors":"Di Wang, Jinhui Xu, Yang He","doi":"10.1109/CISS.2019.8692905","DOIUrl":"https://doi.org/10.1109/CISS.2019.8692905","url":null,"abstract":"In this paper, we study the problem of estimating the covariance matrix under differential privacy, where the underlying covariance matrix is assumed to be sparse and of high dimensions. We propose a new method, called DP-Thresholding, to achieve a non-trivial $l_{2}$-norm based error bound, which is significantly better than the existing ones from adding noise directly to the empirical covariance matrix. Experiments on the synthetic datasets show consistent results with our theoretical claims.","PeriodicalId":123696,"journal":{"name":"2019 53rd Annual Conference on Information Sciences and Systems (CISS)","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122759129","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}
{"title":"Design of Eigenportfolios for US Equities Using Exponential Correlation Model","authors":"A. Akansu, Anqi Xiong","doi":"10.1109/CISS.2019.8692939","DOIUrl":"https://doi.org/10.1109/CISS.2019.8692939","url":null,"abstract":"The eigen decomposition of Toeplitz matrix, with exponential correlations as its elements, to model empirical correlations of US equity returns is investigated. Closed form expressions for eigenvalues and eigenvectors of such Toeplitz matrix are available. Those eigenvectors are used to design the eigenportfolios of the model. The Sharpe ratios and PNL curves of eigenportfolios for stocks in Dow Jones Industrial Average (DJIA) index for the period from July 1999 to Nov. 2018 are calculated to validate the model. The proposed method provides eigenportfolios that closely mimic the eigenportfolios designed based on empirical correlation matrix generated from market data. The modeling of empirical correlation matrix brings new insights to design and evaluate eigenportolios for US equities and other asset classes.","PeriodicalId":123696,"journal":{"name":"2019 53rd Annual Conference on Information Sciences and Systems (CISS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128245518","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}
{"title":"Business-to-Peer Carsharing Systems with Electric Vehicles","authors":"Theodoros Mamalis, S. Bose, L. Varshney","doi":"10.1109/CISS.2019.8692795","DOIUrl":"https://doi.org/10.1109/CISS.2019.8692795","url":null,"abstract":"Carsharing systems are adopting electric vehicles into their fleets and may therefore be able to provide not only transportation services to drivers/passengers but also energy services to the power grid through appropriate participation in electricity markets. This paper develops a queuing model of such carsharing platforms where cars may be deployed for transportation services at a given price, but also for grid services during transportation-idle periods through energy price arbitrage. The model provides a characterization of revenue from each of these two streams. The paper further finds optimal pricing and battery splitting to maximize revenue for the carsharing platform, via an analysis of the reward structure and an optimization algorithm. Platform revenue is assessed for various system parameters under optimal operation.","PeriodicalId":123696,"journal":{"name":"2019 53rd Annual Conference on Information Sciences and Systems (CISS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122612013","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}
{"title":"Statistical QoS-Driven Energy-Efficiency optimization for URLLC Over 5G Mobile Wireless Networks in the Finite Blocklength Regime","authors":"Xi Zhang, Jingqing Wang, H. Poor","doi":"10.1109/CISS.2019.8693052","DOIUrl":"https://doi.org/10.1109/CISS.2019.8693052","url":null,"abstract":"To support delay-bounded multimedia services over 5G mobile wireless networks, the statistical quality-of-service (QoS) technique has been designed to jointly guarantee the statistically delay-bounded video transmissions over different time-varying wireless channels, simultaneously. On the other hand, with stringent delay-bounded and error-rate-bounded QoS requirements for 5G applications, the traditional Shannon capacity is no longer appropriate to characterize the maximum achievable data transmission rate given the block error probability. Towards this end, the finite blocklength coding (FBC) technique has been developed to support the new type of Ultra-Reliable and Low Latency Communications (URLLC). However, since the existing approximations of the transmission rate are neither convex nor concave in terms of the transmit power in the finite blocklength regime, it is challenging to formulate and solve the resource allocation optimization problems for URLLC over various different wireless fading channels while guaranteeing the statistical delay-bounded QoS requirements. To overcome the aforementioned problems, we propose the energy efficient FBC based cross-layer design while guaranteeing the statistical delay-bounded QoS requirements for URLLC. In particular, we establish and analyze FBC based wireless network models. By taking into account the statistical delay-bounded QoS constraints, we formulate and solve the ε-effective energy efficiency optimization problem using FBC. Also conducted is a set of simulations which validate and evaluate our proposed FBC scheme under the statistical delay-bounded QoS constraints for URLLC.","PeriodicalId":123696,"journal":{"name":"2019 53rd Annual Conference on Information Sciences and Systems (CISS)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127032814","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}
{"title":"Online optimization in the Non-Stationary Cloud: Change Point Detection for Resource Provisioning (Invited Paper)","authors":"Jessica Maghakian, Joshua Comden, Zhenhua Liu","doi":"10.1109/CISS.2019.8692890","DOIUrl":"https://doi.org/10.1109/CISS.2019.8692890","url":null,"abstract":"The rapid mainstream adoption of cloud computing and the corresponding spike in the energy usage of big data systems make the efficient management of cloud computing resources a more pressing issue than ever before. To this end, numerous online algorithms such as Receding Horizon Control and Online Balanced Descent have been designed. However it is difficult for cloud service providers to select the best control algorithm dynamically for resource provisioning when confronted with consumer resource demands that are notoriously unpredictable and volatile. Furthermore, it highly possible that it might not be the case for any one algorithm to consistently perform well over the months-long contract period. In this paper, we first exemplify the need to address non-stationarity in cloud computing by showcasing traces from MS Azure. We then develop a novel meta-algorithm that combines change point detection and online optimization. The new algorithm is shown to outperform existing solutions in real-world trace-driven simulations.","PeriodicalId":123696,"journal":{"name":"2019 53rd Annual Conference on Information Sciences and Systems (CISS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130739960","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}
{"title":"Minimax Lower Bound of k-Monotone Estimation in the Sup-norm","authors":"Teresa M. Lebair, Jinglai Shen","doi":"10.1109/CISS.2019.8692914","DOIUrl":"https://doi.org/10.1109/CISS.2019.8692914","url":null,"abstract":"Belonging to the framework of shape constrained estimation, k-monotone estimation refers to the nonparametric estimation of univariate k-monotone functions, e.g., monotone and convex unctions. This paper develops minimax lower bounds for k-monotone regression problems under the sup-norm for general k by constructing a family of k-monotone piecewise polynomial functions (or hypotheses) belonging to suitable Hölder and Sobolev classes. After establishing that these hypotheses satisfy several properties, we employ results from general min-imax lower bound theory to obtain the desired k-monotone regression minimax lower bound. Implications and extensions are also discussed.","PeriodicalId":123696,"journal":{"name":"2019 53rd Annual Conference on Information Sciences and Systems (CISS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131387444","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. Peng, A. Turkmen, Brian Eickhoff, Mark Finta, Paul Gerads
{"title":"Design of a Ground Sampling Distance Graphical User Interface for an Unmanned Aerial Vehicle System","authors":"A. Peng, A. Turkmen, Brian Eickhoff, Mark Finta, Paul Gerads","doi":"10.1109/CISS.2019.8692786","DOIUrl":"https://doi.org/10.1109/CISS.2019.8692786","url":null,"abstract":"This paper describes the design and development of the file configuration and ground sampling distance graphical user interface application for an unmanned aerial vehicle system. It begins with describing the undergraduate capstone project at University of Wisconsin-Stout and its industry project sponsor, Sentera Inc., a company developing sensors, software, and unmanned aerial vehicle systems primarily for agricultural applications. It then presents the needs, design and development, and the implementation of the software application. Agile testing methodology was utilized to improve the functionality of the application. This paper summarizes a capstone project experience with industry sponsor including system design concepts, development of software application, testing methodology, and other technical aspects of the system design leading to a successful undergraduate capstone project.","PeriodicalId":123696,"journal":{"name":"2019 53rd Annual Conference on Information Sciences and Systems (CISS)","volume":"158 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127374703","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}
{"title":"Policy Search in Infinite-Horizon Discounted Reinforcement Learning: Advances through Connections to Non-Convex Optimization : Invited Presentation","authors":"K. Zhang, Alec Koppel, Hao Zhu, T. Başar","doi":"10.1109/CISS.2019.8693017","DOIUrl":"https://doi.org/10.1109/CISS.2019.8693017","url":null,"abstract":"In reinforcement learning (RL), an agent moving through a state space, selects actions which cause a transition to a new state according to an unknown Markov transition density that depends on the previous state and action. After each transition, a reward that informs the quality of being in a particular state is revealed. The goal is to select the action sequence to maximize the long term accumulation of rewards, or value. We focus on the case where the policy that determines how actions are chosen is a fixed stationary distribution parameterized by a vector, the problem horizon is infinite, and the states and actions belong to continuous Euclidean subsets.","PeriodicalId":123696,"journal":{"name":"2019 53rd Annual Conference on Information Sciences and Systems (CISS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125330981","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}
Jonah P. Sengupta, Gaspar Tognetti, P. Pouliquen, A. Andreou
{"title":"Multilevel Storage Cell Characterization and Behavior Modeling of a Crossbar Computational Array in ESF3 Flash Technology : (Invited Paper)","authors":"Jonah P. Sengupta, Gaspar Tognetti, P. Pouliquen, A. Andreou","doi":"10.1109/CISS.2019.8693054","DOIUrl":"https://doi.org/10.1109/CISS.2019.8693054","url":null,"abstract":"Analog and mixed signal vector-matrix multipliers (VMMs) in non-volatile memory cells provide a pathway way to energy and area efficient computation that rivals traditional DSP units. The ability to store multiple bits of data in each floating-gate device for a long amount of time allows for ideal use as hardware accelerators for neural networks. However, current implementations of the technology are impeded by large peripheral circuit overhead. In this work, steps towards a fully-realized NVM-based VMM ASIC are taken. In the 55-nm process, a test array of embedded NOR-flash memory (ESF3) from SST was implemented and fabricated. Multi-bit storage has been demonstrated within the 2x2 array via voltage-mode programming. Secondly, behavioral emulation of the VMM is implemented on a Kintex-7 FPGA to prototype the digital periphery, algorithms, and configurations necessary to embed the NVM-based VMM in a system on chip (SoC). Two quadrant kernel processing is demonstrated at a throughput of 1.8 GOPs for a 72x16 array which can process a 128x128 image @ 250 fps.","PeriodicalId":123696,"journal":{"name":"2019 53rd Annual Conference on Information Sciences and Systems (CISS)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121685241","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}
B. Mondal, V. Sergeev, A. Sengupta, G. Ermolaev, A. Davydov, Eddy Kwon, S. Han, A. Papathanassiou
{"title":"MU-MIMO and CSI Feedback Performance of NR/LTE","authors":"B. Mondal, V. Sergeev, A. Sengupta, G. Ermolaev, A. Davydov, Eddy Kwon, S. Han, A. Papathanassiou","doi":"10.1109/CISS.2019.8692922","DOIUrl":"https://doi.org/10.1109/CISS.2019.8692922","url":null,"abstract":"The Re1–15 physical layer air-interface specifications for NR (5G) and LTE (4G) has been released by 3GPP in September 2018. This paper aims to study two principal gain mechanisms introduced in NR (compared to LTE) targeting spectral efficiency improvements -(i) high order MU-MIMO with up to 12 layer spatially multiplexed transmission and (ii) higher resolution of CSI feedback with Type II feedback mechanism. In order to perform a fair comparison between LTE and NR, we maintain the same overhead, sub-carrier spacing and antenna configurations among other parameters. Although it is known that NR can provide benefits over LTE in terms of deployment flexibility, spectral efficiency and latency using mechanisms like multiple numerology support, lower control channel and reference signal overhead or lower guard bands we believe that the gain mechanisms (i) and (ii) are fundamental and a quantification of this aspect is attractive to operators and vendors who may consider NR or LTE deployments in sub-6 GHz bands.","PeriodicalId":123696,"journal":{"name":"2019 53rd Annual Conference on Information Sciences and Systems (CISS)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121851507","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}