Open AccessPosted Content
Towards Optimally Efficient Search with Deep Learning for Large-Scale MIMO Systems
Reads0
Chats0
TLDR
In this paper, a hyperaccelerated tree search (HATS) algorithm was proposed to solve the optimal signal detection problem in large-scale MIMO systems, which employs a deep neural network (DNN) to estimate the optimal heuristic, and then uses the estimated heuristic to speed up the underlying memory-bounded search algorithm.Abstract:
This paper investigates the optimal signal detection problem with a particular interest in large-scale multiple-input multiple-output (MIMO) systems. The problem is NP-hard and can be solved optimally by searching the shortest path on the decision tree. Unfortunately, the existing optimal search algorithms often involve prohibitively high complexities, which indicates that they are infeasible in large-scale MIMO systems. To address this issue, we propose a general heuristic search algorithm, namely, hyperaccelerated tree search (HATS) algorithm. The proposed algorithm employs a deep neural network (DNN) to estimate the optimal heuristic, and then use the estimated heuristic to speed up the underlying memory-bounded search algorithm. This idea is inspired by the fact that the underlying heuristic search algorithm reaches the optimal efficiency with the optimal heuristic function. Simulation results show that the proposed algorithm reaches almost the optimal bit error rate (BER) performance in large-scale systems, while the memory size can be bounded. In the meanwhile, it visits nearly the fewest tree nodes. This indicates that the proposed algorithm reaches almost the optimal efficiency in practical scenarios, and thereby it is applicable for large-scale systems. Besides, the code for this paper is available at https://github.com/skypitcher/hats.read more
Citations
More filters
Journal ArticleDOI
Distributed Machine Learning for Multiuser Mobile Edge Computing Systems
TL;DR: Simulation results are demonstrated to show that the proposed method can effectively reduce the system cost in terms of latency and energy consumption, and meanwhile ensure more bandwidth and computational capability allocated to the user with a higher taskpriority.
Journal ArticleDOI
Task offloading for vehicular edge computing with imperfect CSI: A deep reinforcement approach
TL;DR: In this paper , a novel deep approach is proposed, which is integrated by deep reinforcement learning (DRL) with the Lagrange multiplier to jointly minimize the system cost and energy consumption.
Journal ArticleDOI
Performance analysis for IRS-assisted MEC networks with unit selection
TL;DR: In this article , the outage performance of the intelligent reflecting surface (IRS)-assisted mobile edge computing (MEC) network, with a single user, a single computational access point (CAP), and a single IRS of N units, where the direct user-CAP link has been disabled, is investigated.
Journal ArticleDOI
Deep reinforcement learning based IRS-assisted mobile edge computing under physical-layer security
TL;DR: In this paper , the authors investigated an intelligent reflecting surface (IRS)-assisted mobile edge computing (MEC) network under physical-layer security, where users can partially offload confidential and compute-intensive tasks to a computing access point (CAP) with the help of the IRS.
Journal ArticleDOI
Intelligent ubiquitous computing for future UAV-enabled MEC network systems
TL;DR: In this paper, the authors investigated intelligent ubiquitous computing for future unmanned aerial vehicle (UAV)-enabled mobile edge computing network (MEC) systems, where multiple users process some computational tasks with the help of one computational access point (CAP), under the jamming from a UAV attack.
References
More filters
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Journal ArticleDOI
Closest point search in lattices
TL;DR: An efficient closest point search algorithm, based on the Schnorr-Euchner (1995) variation of the Pohst (1981) method, is implemented and is shown to be substantially faster than other known methods.
Journal ArticleDOI
On the sphere-decoding algorithm I. Expected complexity
Babak Hassibi,Haris Vikalo +1 more
TL;DR: For the "sphere decoding" algorithm of Fincke and Pohst, a closed-form expression is found for the expected complexity, both for the infinite and finite lattice, which suggests that maximum-likelihood decoding, which was hitherto thought to be computationally intractable, can be implemented in real time.
Journal ArticleDOI
Generalized best-first search strategies and the optimality of A*
Rina Dechter,Judea Pearl +1 more
TL;DR: It is shown that several known properties of A* retain their form and it is also shown that no optimal algorithm exists, but if the performance tests are confirmed to cases in which the estimates are also consistent, then A* is indeed optimal.
Journal ArticleDOI
Algorithm and implementation of the K-best sphere decoding for MIMO detection
Zhan Guo,P. Nilsson +1 more
TL;DR: The implementation results show that it is feasible to achieve near-ML performance and high detection throughput for a 4/spl times/4 16-QAM MIMO system using the proposed algorithms and the VLSI architecture with reasonable complexity.
Related Papers (5)
A Note on Implementation Methodologies of Deep Learning-Based Signal Detection for Conventional MIMO Transmitters
Junjuan Xia,Dan Deng,David Fan +2 more