Linear MIMO Precoders Design for Finite Alphabet Inputs via Model-Free Training
被引:0
作者:
Cao, Chen
论文数: 0引用数: 0
h-index: 0
机构:
Shanghai Jiao Tong Univ, Dept Elect Engn, Shanghai 200240, Peoples R ChinaShanghai Jiao Tong Univ, Dept Elect Engn, Shanghai 200240, Peoples R China
Cao, Chen
[1
]
Feng, Biqian
论文数: 0引用数: 0
h-index: 0
机构:
Shanghai Jiao Tong Univ, Dept Elect Engn, Shanghai 200240, Peoples R ChinaShanghai Jiao Tong Univ, Dept Elect Engn, Shanghai 200240, Peoples R China
Feng, Biqian
[1
]
Wu, Yongpeng
论文数: 0引用数: 0
h-index: 0
机构:
Shanghai Jiao Tong Univ, Dept Elect Engn, Shanghai 200240, Peoples R ChinaShanghai Jiao Tong Univ, Dept Elect Engn, Shanghai 200240, Peoples R China
Wu, Yongpeng
[1
]
Ng, Derrick Wing Kwan
论文数: 0引用数: 0
h-index: 0
机构:
Univ New South Wales, Sch Elect Engn & Telecommun, Sydney, NSW 2052, AustraliaShanghai Jiao Tong Univ, Dept Elect Engn, Shanghai 200240, Peoples R China
Ng, Derrick Wing Kwan
[2
]
Zhang, Wenjun
论文数: 0引用数: 0
h-index: 0
机构:
Shanghai Jiao Tong Univ, Dept Elect Engn, Shanghai 200240, Peoples R ChinaShanghai Jiao Tong Univ, Dept Elect Engn, Shanghai 200240, Peoples R China
Zhang, Wenjun
[1
]
机构:
[1] Shanghai Jiao Tong Univ, Dept Elect Engn, Shanghai 200240, Peoples R China
[2] Univ New South Wales, Sch Elect Engn & Telecommun, Sydney, NSW 2052, Australia
来源:
2022 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2022)
|
2022年
基金:
美国国家科学基金会;
国家重点研发计划;
关键词:
Autoencoders;
deep learning;
finite alphabet;
linear precoders;
MIMO;
OPTIMIZATION;
SIGNALS;
D O I:
10.1109/GLOBECOM48099.2022.10001528
中图分类号:
TP [自动化技术、计算机技术];
学科分类号:
0812 ;
摘要:
This paper investigates a novel method for designing linear precoders with finite alphabet inputs based on autoencoders (AE) without the knowledge of the channel model. By model-free training of the autoencoder in a multiple-input multiple-output (MIMO) system, the proposed method can effectively solve the optimization problem to design the precoders that maximize the mutual information between the channel inputs and outputs, when only the input-output information of the channel can be observed. Specifically, the proposed method regards the receiver and the precoder as two independent parameterized functions in the AE and alternately trains them using the exact and approximated gradient, respectively. Compared with previous precoders design methods, it alleviates the limitation of requiring the explicit channel model to be known. Simulation results show that the proposed method works as well as those methods under known channel models in terms of maximizing the mutual information and reducing the bit error rate.
机构:
Southeast Univ, Natl Mobile Commun Res Lab, Nanjing 210096, Jiangsu, Peoples R ChinaSoutheast Univ, Natl Mobile Commun Res Lab, Nanjing 210096, Jiangsu, Peoples R China
Wu, Yongpeng
Xiao, Chengshan
论文数: 0引用数: 0
h-index: 0
机构:
Missouri Univ Sci & Technol, Dept Elect & Comp Engn, Rolla, MO 65409 USASoutheast Univ, Natl Mobile Commun Res Lab, Nanjing 210096, Jiangsu, Peoples R China
Xiao, Chengshan
Gao, Xiqi
论文数: 0引用数: 0
h-index: 0
机构:
Southeast Univ, Natl Mobile Commun Res Lab, Nanjing 210096, Jiangsu, Peoples R ChinaSoutheast Univ, Natl Mobile Commun Res Lab, Nanjing 210096, Jiangsu, Peoples R China
Gao, Xiqi
Matyjas, John D.
论文数: 0引用数: 0
h-index: 0
机构:
Air Force Res Lab RIT, Rome, NY 13441 USASoutheast Univ, Natl Mobile Commun Res Lab, Nanjing 210096, Jiangsu, Peoples R China
Matyjas, John D.
Ding, Zhi
论文数: 0引用数: 0
h-index: 0
机构:
Univ Calif Davis, Dept Elect & Comp Engn, Davis, CA 95616 USASoutheast Univ, Natl Mobile Commun Res Lab, Nanjing 210096, Jiangsu, Peoples R China
机构:
Qualcomm Res, Div Wireless Res & Dev, San Diego, CA 92121 USAUniv Elect Sci & Technol China, Sch Informat & Commun Engn, Chengdu 610054, Peoples R China
机构:
Southeast Univ, Natl Mobile Commun Res Lab, Nanjing 210096, Jiangsu, Peoples R ChinaSoutheast Univ, Natl Mobile Commun Res Lab, Nanjing 210096, Jiangsu, Peoples R China
Wu, Yongpeng
Wen, Chao-Kai
论文数: 0引用数: 0
h-index: 0
机构:
Natl Sun Yat Sen Univ, Inst Commun Engn, Kaohsiung 804, TaiwanSoutheast Univ, Natl Mobile Commun Res Lab, Nanjing 210096, Jiangsu, Peoples R China
Wen, Chao-Kai
Xiao, Chengshan
论文数: 0引用数: 0
h-index: 0
机构:
Missouri Univ Sci & Technol, Dept Elect & Comp Engn, Rolla, MO 65409 USASoutheast Univ, Natl Mobile Commun Res Lab, Nanjing 210096, Jiangsu, Peoples R China
Xiao, Chengshan
Gao, Xiqi
论文数: 0引用数: 0
h-index: 0
机构:
Southeast Univ, Natl Mobile Commun Res Lab, Nanjing 210096, Jiangsu, Peoples R ChinaSoutheast Univ, Natl Mobile Commun Res Lab, Nanjing 210096, Jiangsu, Peoples R China
Gao, Xiqi
Schober, Robert
论文数: 0引用数: 0
h-index: 0
机构:
Univ Erlangen Nurnberg, Inst Digital Commun, D-91058 Erlangen, GermanySoutheast Univ, Natl Mobile Commun Res Lab, Nanjing 210096, Jiangsu, Peoples R China
机构:
South China Univ Technol, Sch Elect & Informat Engn, Guangzhou 510641, Guangdong, Peoples R ChinaSouth China Univ Technol, Sch Elect & Informat Engn, Guangzhou 510641, Guangdong, Peoples R China
Ke, Feng
Zeng, Weiliang
论文数: 0引用数: 0
h-index: 0
机构:
Qualcomm Res, Div Wireless R&D, San Diego, CA 92121 USASouth China Univ Technol, Sch Elect & Informat Engn, Guangzhou 510641, Guangdong, Peoples R China
Zeng, Weiliang
Xiao, Chengshan
论文数: 0引用数: 0
h-index: 0
机构:
Lehigh Univ, Dept Elect & Comp Engn, Bethlehem, PA 18015 USASouth China Univ Technol, Sch Elect & Informat Engn, Guangzhou 510641, Guangdong, Peoples R China