Dilated Convolution for Time Series Learning
Wang Zhang, Subhro Das, et al.
ICASSP 2025
In this work, we introduce ADAPD, \textbf{A} \textbf{D}ecentr\textbf{A}lized \textbf{P}rimal-\textbf{D}ual algorithmic framework for solving non-convex and smooth consensus optimization problems over a network of distributed agents. The proposed framework relies on a novel problem formulation that elicits ADMM-type updates, where each agent first inexactly solves a local strongly convex subproblem with any method of its choice and then performs a neighbor communication to update a set of dual variables. We present two variants that allow for a single gradient step for the primal updates or multiple communications for the dual updates, to exploit the tradeoff between the per-iteration cost and the number of iterations. When multiple communications are performed, ADAPD can achieve theoretically optimal communication complexity results for non-convex and smooth consensus problems. Numerical experiments on several applications, including a deep-learning one, demonstrate the superiority of ADAPD over several popularly used decentralized methods.
Wang Zhang, Subhro Das, et al.
ICASSP 2025
Rangachari Anand, Kishan Mehrotra, et al.
IEEE Transactions on Neural Networks
Freddy Lécué, Jeff Z. Pan
IJCAI 2013
Rei Odaira, Jose G. Castanos, et al.
IISWC 2013