36,294 Hits in 4.0 sec

Communication-Efficient Distributed Online Learning with Kernels [article]

Michael Kamp, Sebastian Bothe, Mario Boley, Michael Mock
2019 arXiv   pre-print
We propose an efficient distributed online learning protocol for low-latency real-time services.  ...  It extends a previously presented protocol to kernelized online learners that represent their models by a support vector expansion.  ...  of a distributed online learning system.  ... 
arXiv:1911.12899v1 fatcat:rg3ojhwrf5hdtfoy7x4r2wz7b4

Recent Advances in Data-Driven Wireless Communication Using Gaussian Processes: A Comprehensive Survey [article]

Kai Chen, Qinglei Kong, Yijue Dai, Yue Xu, Feng Yin, Lexi Xu, Shuguang Cui
2021 arXiv   pre-print
Furthermore, we review the distributed GPs with promising scalability, which is suitable for applications in wireless networks with a large number of distributed edge devices.  ...  Since GPs achieve the expressive and interpretable learning ability with uncertainty, it is particularly suitable for wireless communication.  ...  Another deep kernel using the finite rank Mercer kernel function with orthogonal embeddings on the last layer has a better learning efficiency and expressiveness [85] .  ... 
arXiv:2103.10134v3 fatcat:bhox7nbavvcb7lnzndu2zr44r4

QC-ODKLA: Quantized and Communication-Censored Online Decentralized Kernel Learning via Linearized ADMM [article]

Ping Xu, Yue Wang, Xiang Chen, Zhi Tian
2022 arXiv   pre-print
We then propose a novel learning framework named Online Decentralized Kernel learning via Linearized ADMM (ODKLA) to efficiently solve the online decentralized kernel learning problem.  ...  This paper focuses on online kernel learning over a decentralized network.  ...  online kernel learning to efficiently solve the online kernel learning problem over a decentralized network.  ... 
arXiv:2208.02777v1 fatcat:pwwv4332fnh3zhm4vhpmqo3f2u

A Survey on Dynamic Structure Embedded Online Multiple-Output Regression for Streaming Data

Priyanka K. Kendre
2020 International Journal for Research in Applied Science and Engineering Technology  
In this way online multiple-output regression uses the techniques of machine learning system for modeling correlated data stream and predicting multidimensional related data stream and it always provides  ...  It can work with various side information sources that are communicated as different kernels.  ...  Kernelized matrix factorization extends with full Bayesian treatment and it can work with various side data sources that are communicated at different kernels.  ... 
doi:10.22214/ijraset.2020.5427 fatcat:7hgozu4wbjey7nfxv3mf4j4qju

Optimally Compressed Nonparametric Online Learning [article]

Alec Koppel, Amrit Singh Bedi, Ketan Rajawat, Brian M. Sadler
2020 arXiv   pre-print
Unfortunately, when used online, nonparametric methods suffer a "curse of dimensionality" which precludes their use: their complexity scales at least with the time index.  ...  Further, the applications to robotics, communications, economics, and power are discussed, as well as extensions to multi-agent systems.  ...  Online multi-agent learning with nonlinear models may pave the pathway for next-generation distributed intelligence.  ... 
arXiv:1909.11555v2 fatcat:z2tl34d7nbazdlzfmwrsw5rzfu

Are we still friends: Kernel multivariate survival analysis

Shiyu Liang, Ruotian Luo, Ge Chen, Songjun Ma, Weijie Wu, Li Song, Xiaohua Tian, Xinbing Wang
2014 2014 IEEE Global Communications Conference  
Furthermore, to avoid the high computational complexity in kernel learning we impose sparsity in our model.  ...  Therefore, precisely modeling and predicting state of each online relationship is worthwhile in many respects. For social communication services such modeling permits new and novel online services.  ...  Although a support vector machine learning method with kernel function was proposed to fit in nonlinear dependencies, a learning algorithm with computational complexity up to O(n 3 ) and memory requirement  ... 
doi:10.1109/glocom.2014.7036842 dblp:conf/globecom/LiangLCMWSTW14 fatcat:hdsts7w5zzfmfm5lteisgm7qaq

Communication-Efficient Online Federated Learning Framework for Nonlinear Regression [article]

Vinay Chakravarthi Gogineni, Stefan Werner, Yih-Fang Huang, Anthony Kuh
2021 arXiv   pre-print
Experimental results show that PSO-Fed can achieve competitive performance with a significantly lower communication overhead than Online-Fed.  ...  Some recent works introduced a framework for online FL (Online-Fed) wherein clients perform model learning on streaming data and communicate the model to the server; however, they do not address the associated  ...  Our solution to this problem stems from a different approach, namely, partial-sharing concepts [24, 25] that are very attractive for communication-efficient distributed learning.  ... 
arXiv:2110.06556v1 fatcat:iirn6aqp4rg53ofe4vtqirtgty

Distributed Online Learning with Multiple Kernels [article]

Jeongmin Chae, Songnam Hong
2021 arXiv   pre-print
For this model, we propose a novel learning framework with multiple kernels, which is named DOMKL.  ...  This learning model is called a fully distributed online learning (or a fully decentralized online federated learning).  ...  Thus, it is still an open problem to construct an efficient multiple kernel-based algorithm for distributed online learning tasks, which is the primary motivation of this paper.  ... 
arXiv:2102.12733v2 fatcat:f33baqmi3fd7heprbyhcbsjja4

2019 Index IEEE Transactions on Signal and Information Processing over Networks Vol. 5

2019 IEEE Transactions on Signal and Information Processing over Networks  
., +, TSIPN Dec. 2019 779-791 Asynchronous Online Learning in Multi-Agent Systems With Proximity Constraints.  ...  Yan, J., +, TSIPN March 2019 168-180 L Learning (artificial intelligence) Asynchronous Online Learning in Multi-Agent Systems With Proximity Constraints.  ... 
doi:10.1109/tsipn.2019.2959414 fatcat:ixpx5rg5l5hshkt2ppvie3afqe

Meta-Learning Priors for Efficient Online Bayesian Regression [article]

James Harrison, Apoorva Sharma, Marco Pavone
2018 arXiv   pre-print
space yields accurate online predictions of the posterior predictive density.  ...  scalability and data-efficiency are important.  ...  While the ALPaCA model has shown potential for efficient online Bayesian learning, it has several limitations.  ... 
arXiv:1807.08912v2 fatcat:l2m2oohlyzdrxbcsk7a2t5piii

Online feature extraction for the incremental learning of gestures in human-swarm interaction

Jawad Nagi, Alessandro Giusti, Farrukh Nagi, Luca M. Gambardella, Gianni A. Di Caro
2014 2014 IEEE International Conference on Robotics and Automation (ICRA)  
To learn and classify gestures in an online and incremental fashion, we employ a 2nd order online learning method, namely the Soft-Confidence Weighted (SCW) learning scheme.  ...  We present a novel approach for the online learning of hand gestures in swarm robotic (multi-robot) systems.  ...  The authors participate in Project 4: Distributed Robotics, sub-project 4.5, Symbiotic human-swarm cooperation.  ... 
doi:10.1109/icra.2014.6907338 dblp:conf/icra/NagiGNGC14 fatcat:7menzlmu6zh4rc5ckhvahdga7m

Data-driven online variational filtering in wireless sensor networks

Hichem Snoussi, Jean-Yves Tourneret, Petar M. Djuric, Cedric Richard
2009 2009 IEEE International Conference on Acoustics, Speech and Signal Processing  
Index Terms-Bayesian filtering, sensor networks, machine learning.  ...  Based on a few selected sensors, target tracking is performed distributively without any information about the observation model.  ...  Following the kernel trick, commonly used in the machine learning community, the similarity measurements are considered as scalar products in a reproducing kernel Hilbert space (RKHS).  ... 
doi:10.1109/icassp.2009.4960108 dblp:conf/icassp/SnoussiTDR09 fatcat:jj6alrg6g5f5xg5voi6qhn5yuy

Kernel-based Online Learning for Real-Time Voltage Control in Distribution Networks

Lisette Cupelli, Alejandro Esteban Otero, Ferdinanda Ponci, Antonello Monti
2020 IET Smart Grid  
Specifically, the proposed datadriven approach uses functional stochastic gradient descent in Reproducing Kernel Hilbert Spaces (RKHSs), to learn the control strategies for Distributed Generation (DG)  ...  This paper presents a new data-driven voltage control approach for distribution networks based on kernel methods.  ...  Online learning with kernels has not yet being proposed to learn strategies for controlled assets.  ... 
doi:10.1049/iet-stg.2019.0312 fatcat:j5xcoiybxja4dgnhppiazc3y4q

Kernel Association for Classification and Prediction: A Survey

Yuichi Motai
2015 IEEE Transactions on Neural Networks and Learning Systems  
This survey outlines the latest trends and innovations of a kernel framework for big data analysis. KA topics include offline learning, distributed database, online learning, and its prediction.  ...  techniques for nonlinear optimal filter implementations. 3) Explore kernel selection for distributed databases including solutions of heterogeneous issues.  ...  DISTRIBUTED DATABASE WITH KERNEL Various KAs using offline learning may be extended to address big data by considering distributed databases.  ... 
doi:10.1109/tnnls.2014.2333664 pmid:25029489 fatcat:cotcvbtpk5fcpkwgwpg26b6clu

Support vector machine based machine learning method for GS 8QAM constellation classification in seamless integrated fiber and visible light communication system

Wenqing Niu, Yinaer Ha, Nan Chi
2020 Science China Information Sciences  
Support vector machine based machine learning method for GS 8QAM constellation classification in seamless integrated fiber and visible light communication system.  ...  Visible light communication (VLC) network over optical fiber has become a potential candidate in ultra-high speed indoor wireless communication.  ...  To establish efficient machine learning model, besides adjusting the parameters of SVM, size of training set is also critical.  ... 
doi:10.1007/s11432-019-2850-3 fatcat:cj2frxopnbdhrmc53qh6kpwyw4
« Previous Showing results 1 — 15 out of 36,294 results