Decentralized Projection-free Online Upper-Linearizable Optimization with Applications to DR-Submodular Optimization

Excerpt

arXiv:2501.18183v3 Announce Type: replace-cross Abstract: We introduce a novel framework for decentralized projection-free optimization, extending projection-free methods to a broader class of upper-linearizable functions. Our approach leverages decentralized optimization techniques with the flexibility of upper-linearizable function frameworks, effectively generalizing traditional DR-submodular function optimization. We obtain the regret of $O(T^{1-\theta/2})$ with communication complexity of $