TY - JOUR
T1 - Learning to Broadcast for Ultra-Reliable Communication With Differential Quality of Service via the Conditional Value at Risk
AU - Karasik, Roy
AU - Simeone, Osvaldo
AU - Jang, Hyeryung
AU - Shitz, Shlomo Shamai
N1 - Publisher Copyright:
© 1972-2012 IEEE.
PY - 2022/12/1
Y1 - 2022/12/1
N2 - Broadcast/multicast communication systems are typically designed to optimize the outage rate criterion, which neglects the performance of the fraction of clients with the worst channel conditions. Targeting ultra-reliable communication scenarios, this paper takes a complementary approach by introducing the conditional value-at-risk (CVaR) rate as the expected rate of a worst-case fraction of clients. To support differential quality-of-service (QoS) levels in this class of clients, layered division multiplexing (LDM) is applied, which enables decoding at different rates. Focusing on a practical scenario in which the transmitter does not know the fading distribution, layer allocation is optimized based on a dataset sampled offline. The optimality gap caused by the availability of limited data is bounded via a generalization analysis, and the sample complexity is shown to increase as the designated fraction of worst-case clients decreases. Considering this theoretical result, meta-learning is introduced as a means to reduce sample complexity by leveraging data from previous deployments. Numerical experiments demonstrate that LDM improves spectral efficiency even for small datasets; that, for sufficiently large datasets, the proposed mirror-descent-based layer optimization scheme achieves a CVaR rate close to that achieved when the transmitter knows the fading distribution; and that meta-learning can significantly reduce data requirements.
AB - Broadcast/multicast communication systems are typically designed to optimize the outage rate criterion, which neglects the performance of the fraction of clients with the worst channel conditions. Targeting ultra-reliable communication scenarios, this paper takes a complementary approach by introducing the conditional value-at-risk (CVaR) rate as the expected rate of a worst-case fraction of clients. To support differential quality-of-service (QoS) levels in this class of clients, layered division multiplexing (LDM) is applied, which enables decoding at different rates. Focusing on a practical scenario in which the transmitter does not know the fading distribution, layer allocation is optimized based on a dataset sampled offline. The optimality gap caused by the availability of limited data is bounded via a generalization analysis, and the sample complexity is shown to increase as the designated fraction of worst-case clients decreases. Considering this theoretical result, meta-learning is introduced as a means to reduce sample complexity by leveraging data from previous deployments. Numerical experiments demonstrate that LDM improves spectral efficiency even for small datasets; that, for sufficiently large datasets, the proposed mirror-descent-based layer optimization scheme achieves a CVaR rate close to that achieved when the transmitter knows the fading distribution; and that meta-learning can significantly reduce data requirements.
KW - Broadcasting/multicasting
KW - CVaR
KW - LDM
KW - meta-learning
KW - ultra-reliable communication
UR - http://www.scopus.com/inward/record.url?scp=85141579168&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85141579168&partnerID=8YFLogxK
U2 - 10.1109/TCOMM.2022.3219118
DO - 10.1109/TCOMM.2022.3219118
M3 - Article
AN - SCOPUS:85141579168
SN - 0090-6778
VL - 70
SP - 8060
EP - 8074
JO - IEEE Transactions on Communications
JF - IEEE Transactions on Communications
IS - 12
ER -