The paper proposes a heterogeneous push-sum based subgradient algorithm for multi-agent distributed convex optimization in which each agent can arbitrarily switch between subgradient-push and push-subgradient at each time. It is shown that the heterogeneous algorithm converges to an optimal point at an optimal rate over time-varying directed graphs.
@article{arxiv.2303.17060,
title = {Heterogeneous Distributed Subgradient},
author = {Yixuan Lin and Ji Liu},
journal= {arXiv preprint arXiv:2303.17060},
year = {2023}
}
Comments
arXiv admin note: text overlap with arXiv:2203.16623