TY - GEN
T1 - A decentralized prediction-correction method for networked time-varying convex optimization
AU - Simonetto, Andrea
AU - Mokhtari, Aryan
AU - Koppel, Alec
AU - Leus, Geert
AU - Ribeiro, Alejandro
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/1/1
Y1 - 2015/1/1
N2 - We study networked unconstrained convex optimization problems where the objective function changes continuously in time. We propose a decentralized algorithm (DePCoT) with a discrete time-sampling scheme to find and track the solution trajectory based on prediction and gradient-based correction steps, while sampling the problem data at a constant sampling period h. Under suitable conditions and for limited sampling periods, we establish that the asymptotic error bound behaves as O(h2), which outperforms the state of the art existing error bound of O(h) for correction-only methods. The key contributions are the prediction step and a decentralized method to approximate the inverse of the Hessian of the cost function in a decentralized way, which yields quantifiable trade-offs between communication and accuracy.
AB - We study networked unconstrained convex optimization problems where the objective function changes continuously in time. We propose a decentralized algorithm (DePCoT) with a discrete time-sampling scheme to find and track the solution trajectory based on prediction and gradient-based correction steps, while sampling the problem data at a constant sampling period h. Under suitable conditions and for limited sampling periods, we establish that the asymptotic error bound behaves as O(h2), which outperforms the state of the art existing error bound of O(h) for correction-only methods. The key contributions are the prediction step and a decentralized method to approximate the inverse of the Hessian of the cost function in a decentralized way, which yields quantifiable trade-offs between communication and accuracy.
U2 - 10.1109/CAMSAP.2015.7383848
DO - 10.1109/CAMSAP.2015.7383848
M3 - Conference contribution
AN - SCOPUS:84963812920
T3 - 2015 IEEE 6th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2015
SP - 509
EP - 512
BT - 2015 IEEE 6th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2015
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 6th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2015
Y2 - 13 December 2015 through 16 December 2015
ER -