TY - GEN
T1 - Unsupervised Learning of Adaptive Codebooks for Deep Feedback Encoding in FDD Systems
AU - Turan, Nurettin
AU - Koller, Michael
AU - Bazzi, Samer
AU - Xu, Wen
AU - Utschick, Wolfgang
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - In this work, we propose a joint adaptive codebook construction and feedback generation scheme in frequency divi-sion duplex (FDD) systems. Both unsupervised and supervised deep learning techniques are used for this purpose. Based on a recently discovered equivalence of uplink (UL) and downlink (DL) channel state information (CSI) in terms of neural network learning, the codebook and associated deep encoder for feedback signaling is based on UL data only. Subsequently, the feedback encoder can be offloaded to the mobile terminals (MTs) to generate channel feedback there as efficiently as possible, without any training effort at the terminals or corresponding transfer of training and codebook data. Numerical simulations demonstrate the promising performance of the proposed method.
AB - In this work, we propose a joint adaptive codebook construction and feedback generation scheme in frequency divi-sion duplex (FDD) systems. Both unsupervised and supervised deep learning techniques are used for this purpose. Based on a recently discovered equivalence of uplink (UL) and downlink (DL) channel state information (CSI) in terms of neural network learning, the codebook and associated deep encoder for feedback signaling is based on UL data only. Subsequently, the feedback encoder can be offloaded to the mobile terminals (MTs) to generate channel feedback there as efficiently as possible, without any training effort at the terminals or corresponding transfer of training and codebook data. Numerical simulations demonstrate the promising performance of the proposed method.
KW - Lloyd-Max quanti-zation
KW - Projected gradient descent
KW - feedback codebook design
KW - frequency division duplexing
KW - neural network classification
UR - http://www.scopus.com/inward/record.url?scp=85124534067&partnerID=8YFLogxK
U2 - 10.1109/IEEECONF53345.2021.9723406
DO - 10.1109/IEEECONF53345.2021.9723406
M3 - Conference contribution
AN - SCOPUS:85124534067
T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers
SP - 1464
EP - 1469
BT - 55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021
A2 - Matthews, Michael B.
PB - IEEE Computer Society
T2 - 55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021
Y2 - 31 October 2021 through 3 November 2021
ER -