Filters








16 Hits in 6.1 sec

Task Replication for Vehicular Edge Computing: A Combinatorial Multi-Armed Bandit based Approach [article]

Yuxuan Sun, Jinhui Song, Sheng Zhou, Xueying Guo, Zhisheng Niu
2018 arXiv   pre-print
To improve the QoS of VEC and exploit the abundant computing resources on vehicles, we propose a learning-based task replication algorithm (LTRA) based on combinatorial multi-armed bandit (CMAB) theory  ...  In vehicular edge computing (VEC) system, some vehicles with surplus computing resources can provide computation task offloading opportunities for other vehicles or pedestrians.  ...  In this paper, we propose a learning-based task replication algorithm (LTRA) based on combinatorial multi-armed bandit (CMAB) theory [17] .  ... 
arXiv:1807.05718v1 fatcat:bt576spo5jfyhnagmitept4ddq

Distributed Task Replication for Vehicular Edge Computing: Performance Analysis and Learning-based Algorithm [article]

Yuxuan Sun, Sheng Zhou, Zhisheng Niu
2020 arXiv   pre-print
Based on the analytical result, we design a learning-based task replication algorithm (LTRA) with combinatorial multi-armed bandit theory, which works in a distributed manner and can automatically adapt  ...  In a vehicular edge computing (VEC) system, vehicles can share their surplus computation resources to provide cloud computing services.  ...  DISTRIBUTED TASK REPLICATION ALGORITHM: A COMBINATORIAL MULTI-ARMED BANDIT BASED APPROACH Based on the optimized number of task replicas K * , we design a distributed task replication algorithm in this  ... 
arXiv:2002.08833v1 fatcat:ks6i3msj2vfu5mbnfeqpllssgi

2021 Index IEEE Transactions on Mobile Computing Vol. 20

2022 IEEE Transactions on Mobile Computing  
Multi-Armed Bandits.  ...  Computing: A Multi-Task Learning Approach.  ... 
doi:10.1109/tmc.2021.3133125 fatcat:xbdfaozpkjbbjm3gfbmxcmzj6i

Convergence of Edge Computing and Deep Learning: A Comprehensive Survey [article]

Xiaofei Wang and Yiwen Han and Victor C.M. Leung and Dusit Niyato and Xueqiang Yan and Xu Chen
2019 arXiv   pre-print
In addition, DL, as the representative technique of artificial intelligence, can be integrated into edge computing frameworks to build intelligent edge for dynamic, adaptive edge maintenance and management  ...  Thus, unleashing DL services using resources at the network edge near the data sources has emerged as a desirable solution.  ...  Similarly, DRL is also used in [111] to obtain the optimal task offloading policy in vehicular edge computing.  ... 
arXiv:1907.08349v2 fatcat:4hfqgdto4fhvlguwfjxuz3ik5q

Learning-based decentralized offloading decision making in an adversarial environment

Byungjin Cho, Yu Xiao
2021 IEEE Transactions on Vehicular Technology  
Index Terms-Vehicular fog computing, task offloading, online learning, adversarial multi-armed bandit.  ...  In this article, we develop a new adversarial online learning algorithm with bandit feedback based on the adversarial multi-armed bandit theory, to enable scalable and low-complexity offloading decision  ...  The work in [20] proposed a learning-based task replication algorithm based on combinatorial MAB, where task replicas can be offloaded to multiple vehicles to be processed simultaneously.  ... 
doi:10.1109/tvt.2021.3115899 fatcat:uyb4cqyohra6zaxmghxobbyyse

Learning-based decentralized offloading decision making in an adversarial environment [article]

Byungjin Cho, Yu Xiao
2021 arXiv   pre-print
In this article, we develop a new adversarial online learning algorithm with bandit feedback based on the adversarial multi-armed bandit theory, to enable scalable and low-complexity offloading decision  ...  Vehicular fog computing (VFC) pushes the cloud computing capability to the distributed fog nodes at the edge of the Internet, enabling compute-intensive and latency-sensitive computing services for vehicles  ...  The work in [20] proposed a learning-based task replication algorithm based on combinatorial MAB, where task replicas can be offloaded to multiple vehicles to be processed simultaneously.  ... 
arXiv:2104.12827v3 fatcat:tytvfmmmb5grngvyhuh4nayez4

2021 Index IEEE Transactions on Wireless Communications Vol. 20

2021 IEEE Transactions on Wireless Communications  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  ., +, TWC April 2021 2565-2578 Distributed Task Replication for Vehicular Edge Computing: Performance Analysis and Learning-Based Algorithm.  ...  ., +, TWC April 2021 2565-2578 Distributed Task Replication for Vehicular Edge Computing: Performance Analysis and Learning-Based Algorithm.  ... 
doi:10.1109/twc.2021.3135649 fatcat:bgd3vzb7pbee7jp75dnbucihmq

Design of large polyphase filters in the Quadratic Residue Number System

Gian Carlo Cardarilli, Alberto Nannarelli, Yann Oster, Massimo Petricca, Marco Re
2010 2010 Conference Record of the Forty Fourth Asilomar Conference on Signals, Systems and Computers  
We demonstrate the computational adequacy of this approach on the practical task of keyword spotting.  ...  The edge maps are generated from a novel Bi-dimensional Empirical Mode Decomposition (BEMD) based edge detection method.  ... 
doi:10.1109/acssc.2010.5757589 fatcat:ccxnu5owr5fyrcjcqukumerueq

User-Centric Radio Access Technology Selection: A Survey of Game Theory Models and Multi-Agent Learning Algorithms

Giuseppe Caso, Ozgu Alay, Guido Carlo Ferrante, Luca De Nardis, Maria-Gabriella Di Benedetto, Anna Brunstrom
2021 IEEE Access  
learning (RL) schemes, and also including most recent approaches, such as deep RL (DRL) and multi-armed bandit (MAB).  ...  Cognition: The increased cognitive and computational capabilities of user devices enable autonomous rational decisions based on context-awareness at the user end, i.e., by observing and adapting to the  ...  A similar observation can be done for novel vehicular communications, for which initial GT-based RAT selection approaches can be found in [261] [262] .  ... 
doi:10.1109/access.2021.3087410 fatcat:xjqicfhgdfgy3n6ffss7ppvn44

Bandit-based Delay-Aware Service Function Chain Orchestration at the Edge [article]

Lei Wang, University Of Calgary, Majid Ghaderi
2021
In this paper, we formulate the user-managed SFC placement in MEC as a contextual combinatorial multi-arm bandit (C2MAB) problem and proposed BandEdge, a bandit-based algorithm for online SFC placement  ...  Mobile Edge Computing (MEC) enables both cloud computing and edge computing for mobile users, providing them with intensive computing resources and proximity to the data sources.  ...  this problem, we formulated the user-managed SFC placement in MEC as a contextual combinatorial multi-arm bandit (C 2 MAB) problem and proposed CHANGE, a bandit-based algorithm for online SFC orchestration  ... 
doi:10.11575/prism/38760 fatcat:bj4bcnepsfhcvlcvdqd6mdxs6a

AI and ML – Enablers for Beyond 5G Networks

Alexandros Kaloxylos, Anastasius Gavras, Daniel Camps Mur, Mir Ghoraishi, Halid Hrasnica
2020 Zenodo  
This white paper on AI/ML as enablers of 5G and B5G networks is based on contributions from 5G PPP projects that research, implement and validate 5G and B5G network systems.  ...  Reinforcement learning is concerned about how intelligent agents must take actions in order to maximize a collective reward, e.g. to improve a property of the system.  ...  Reinforcement learning approaches, such as based on multi-armed-bandit, are receiving much attention currently and have been shown to be able to yield promising results [309] , [165] .  ... 
doi:10.5281/zenodo.4299895 fatcat:ngzbopfm6bb43lnrmep6nz5icm

A/B Testing [chapter]

2017 Encyclopedia of Machine Learning and Data Mining  
This demonstrates the power provided by the input vectors (also called side observations or side information), because such a result is not possible in the standard multi-armed bandit problem, which corresponds  ...  Other approaches to abduction include set covering (See, e.g., Reggia 1983) or case-based explanation, (e.g., Leake 1995). The following explanation uses a logic-based approach.  ...  In the presence of linear function approximation, the average-reward version of temporal difference learning, which learns a state-based value function for a fixed policy, is shown to converge in the limit  ... 
doi:10.1007/978-1-4899-7687-1_100507 fatcat:bg6sszljsrax5heho4glbcbicu

Average-Payoff Reinforcement Learning [chapter]

2017 Encyclopedia of Machine Learning and Data Mining  
This demonstrates the power provided by the input vectors (also called side observations or side information), because such a result is not possible in the standard multi-armed bandit problem, which corresponds  ...  Other approaches to abduction include set covering (See, e.g., Reggia 1983) or case-based explanation, (e.g., Leake 1995). The following explanation uses a logic-based approach.  ...  In the presence of linear function approximation, the average-reward version of temporal difference learning, which learns a state-based value function for a fixed policy, is shown to converge in the limit  ... 
doi:10.1007/978-1-4899-7687-1_100029 fatcat:jub4ulyg45abnf4qgutimczie4

Scientific Visualization (Dagstuhl Seminar 11231) Outdoor and Large-Scale Real-World Scene Analysis. 15th Workshop Theoretic Foundations of Computer Vision

Min Chen, Hans Hagen, Charles Hansen, Arie Kaufman, Martin Dyer, Uriel Feige, Alan Frieze, Marek Karpinski, Frank Dellaert, Jan-Michael Frahm, Marc Pollefeys, Bodo Rosenhahn
2011 unpublished
Thanks go to Mathias Hauptmann for his help in collecting abstracts of the talks and other related materials for these Proceedings.  ...  We thank Annette Beyer and Angelika Mueller-von Brochowski for their continuous support and help in organizing this workshop.  ...  Together with a novel ambient occlusion approach, these multi-field properties provide the means for feature-based and interactive visualization of dense line data.  ... 
fatcat:jzxttttmrvda3caw6dy4q2kw6i

Dagstuhl Reports, Volume 7, Issue 7, July 2017, Complete Issue [article]

2018
bandits.  ...  There were also discussions around what automatic adjustments to design could be made so that an existing project or tasks could easily be replicated or made suitable for a different demographic group.  ...  Task for Technicality Measurement For our Information Nutrition Label, we want to calculate a technicalness score, or technicality, for a document that indicates how hard it would be to understand for  ... 
doi:10.4230/dagrep.7.7 fatcat:ve4n3wvvk5bkfgae36nsto7sre
« Previous Showing results 1 — 15 out of 16 results