The paper introduces Dec-BFTRL, a decentralized algorithm for online optimization of upper-linearizable payoffs with efficient separation access, targeting continuous diminishing-return submodular maximization. Each agent evaluates its action against the average of local objectives, projects via an approximate gauge, exchanges a cumulative surrogate-gradient dual state, and uses a local HybridNewton step to minimize its BFTRL potential. The method achieves an expected network-aggregate regret of “~O(√T)” while requiring T neighbor-mixing steps and ~O(T) separation-oracle calls per agent, and provides four wrapper instantiations for three DR-submodular problems.
By Yiyang Lu, Mohammad Pedramfar, Vaneet Aggarwal
arXiv:2610. 29261v1 Announce Type: cross Abstract: We study group distributionally robust optimization (GDRO) over decentralized networks, where workers collaborate to learn robust models by minimizing the maximum local risk.
By Haomin Bai, Junyan Sun, Quan Cheng, Yuanyu Wan, Lijun Zhang
We study group distributionally robust optimization (GDRO) over decentralized networks, where workers collaborate to learn robust models by minimizing the maximum local risk. Existing methods optimize...
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-...
By Yiyang Lu, Mohammad Pedramfar, Vaneet Aggarwal
The paper presents an online algorithm that achieves the same $0.401$ approximation factor for maximizing nonnegative, non-monotone DR-submodular functions over compact convex down-closed subsets of the $d$-dimensional unit cube as the best known offline construction. In the full-information value-oracle model, the algorithm attains this factor with sublinear regret, using $O(dT^{1/4})$ oracle calls per round and $O(T^{3/4})$ regret, and offers flexible batching trade-offs. Under a positive-anchor condition, a randomized blocking strategy preserves the $0.401$ factor while achieving $O(T^{5/6})$ one-point bandit regret.
By Vaneet Aggarwal, Yiyang Lu
arXiv:2610. 10527v1 Announce Type: cross Abstract: Heavy-tailed noise has been widely observed in modern machine learning, motivating the use of methods like gradient clipping and normalization.
By Aleksandar Armacki, Haoyuan Cai, Ali H. Sayed
arXiv:2602. 20578v2 Announce Type: replace Abstract: We study online maximization of non-monotone Diminishing-Return(DR)-submodular functions over down-closed convex sets, a regime where existing projection-free online methods suffer from suboptimal regret and limited feedback guarantees.
By Yiyang Lu, Haresh Jadav, Mohammad Pedramfar, Ranveer Singh, Vaneet Aggarwal
arXiv:2603. 27803v2 Announce Type: replace Abstract: We provide a distributed online algorithm for multi-agent submodular maximization under communication delays.
By Zirui Xu, Vasileios Tzoumas
arXiv:2608. 12134v1 Announce Type: cross Abstract: We study nonnegative submodular maximization subject to a general matroid when the offline algorithm is given an arbitrary controlled value oracle.
By Vaneet Aggarwal
arXiv:2603. 19617v2 Announce Type: replace Abstract: Federated learning (FL) is a communication-efficient framework for solving distributed optimization problems.
By Mohammadjavad Ebrahimi, Daniel Burbano, Farzad Yousefian
arXiv:2607. 01665v1 Announce Type: new Abstract: Decentralized online convex optimization (D-OCO) is a popular framework for distributed applications with streaming data.
By Hao Zhou, Xiaoyu Wang, Chang Yao, Mingli Song, Yuanyu Wan
arXiv:2502. 16744v3 Announce Type: replace Abstract: In adversarial Constrained Online Convex Optimization (COCO), a learner selects actions from a fixed convex set while seeking both low regret and low cumulative constraint violation (CCV) under time-varying constraints.
By Yiyang Lu, Mohammad Pedramfar, Mengbo Wang, Vaneet Aggarwal