TY - GEN
T1 - Decentralized optimization over noisy, rate-constrained networks
T2 - 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021
AU - Saha, Rajarshi
AU - Rini, Stefano
AU - Rao, Milind
AU - Goldsmith, Andrea
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - In decentralized optimization, multiple nodes in a network collaborate to minimize the sum of their local loss functions. The information exchange between nodes required for this task is often limited by network connectivity. We consider a generalization of this setting, in which communication is further hindered by (i) a finite data-rate constraint on the signal transmitted by any node, and (ii) an additive noise corrupting the signal received by any node. We develop a novel algorithm for this scenario: Decentralized Lazy Mirror Descent with Differential Exchanges (DLMD-DiffEx), which guarantees convergence of the local estimates to the optimal solution. A salient feature of DLMD-DiffEx is the introduction of additional proxy variables that are maintained by the nodes to account for the disagreement in their estimates due to channel noise and data-rate constraints. We investigate the performance of DLMD-DiffEx both from a theoretical perspective as well as through numerical evaluations.
AB - In decentralized optimization, multiple nodes in a network collaborate to minimize the sum of their local loss functions. The information exchange between nodes required for this task is often limited by network connectivity. We consider a generalization of this setting, in which communication is further hindered by (i) a finite data-rate constraint on the signal transmitted by any node, and (ii) an additive noise corrupting the signal received by any node. We develop a novel algorithm for this scenario: Decentralized Lazy Mirror Descent with Differential Exchanges (DLMD-DiffEx), which guarantees convergence of the local estimates to the optimal solution. A salient feature of DLMD-DiffEx is the introduction of additional proxy variables that are maintained by the nodes to account for the disagreement in their estimates due to channel noise and data-rate constraints. We investigate the performance of DLMD-DiffEx both from a theoretical perspective as well as through numerical evaluations.
KW - Additive channel noise
KW - Decentralized optimization
KW - Finite data-rate constraint
KW - Lazy mirror descent
UR - http://www.scopus.com/inward/record.url?scp=85115099225&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85115099225&partnerID=8YFLogxK
U2 - 10.1109/ICASSP39728.2021.9413527
DO - 10.1109/ICASSP39728.2021.9413527
M3 - Conference contribution
AN - SCOPUS:85115099225
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 5055
EP - 5059
BT - 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 6 June 2021 through 11 June 2021
ER -