paper-with-me

홈 › Papers

One Gradient Frank-Wolfe for Decentralized Online Convex and Submodular Optimization

2022-10-30 · Tuan-Anh Nguyen, Nguyen Kim Thang, Denis Trystram

Decentralized learning has been studied intensively in recent years motivated by its wide applications in the context of federated learning. The majority of previous research focuses on the offline setting in which the objective function is static. However, the offline setting becomes unrealistic in numerous machine learning applications that witness the change of massive data. In this paper, we propose \emph{decentralized online} algorithm for convex and continuous DR-submodular optimization, two classes of functions that are present in a variety of machine learning problems. Our algorithms achieve performance guarantees comparable to those in the centralized offline setting. Moreover, on average, each participant performs only a \emph{single} gradient computation per time step. Subsequently, we extend our algorithms to the bandit setting. Finally, we illustrate the competitive performance of our algorithms in real-world experiments.

📄 PDF Abstract BibTeX arXiv:2210.16790

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Boosted Stochastic Frank-Wolfe for Constrained Nonconvex Optimization

2026-05-24 · Navil Nandhan, Abbas Khademi, Antonio Silveti-Falls arxiv

The boosted Frank-Wolfe algorithm accelerates the classical Frank-Wolfe algorithm by better aligning the update direction with the negative gradient. Its analysis, however, has been limited to deterministic convex proble…

Decentralized Frank-Wolfe Algorithm for Convex and Non-convex Problems

2016-12-05 · Hoi-To Wai, Jean Lafond, Anna Scaglione, Eric Moulines

Decentralized optimization algorithms have received much attention due to the recent advances in network information processing. However, conventional decentralized algorithms based on projected gradient descent are inca…

Matrix CompletionSparse Learning

Revisiting Frank-Wolfe for Structured Nonconvex Optimization

2025-03-11 · Hoomaan Maskan, Yikun Hou, Suvrit Sra, Alp Yurtsever

We introduce a new projection-free (Frank-Wolfe) method for optimizing structured nonconvex functions that are expressed as a difference of two convex functions. This problem class subsumes smooth nonconvex minimization,…

Computational Efficiency

Online Decentralized Frank-Wolfe: From theoretical bound to applications in smart-building

2022-07-31 · Angan Mitra, Nguyen Kim Thang, Tuan-Anh Nguyen, Denis Trystram 외

The design of decentralized learning algorithms is important in the fast-growing world in which data are distributed over participants with limited local computation resources and communication. In this direction, we pro…

Faster Projection-free Online Learning

2020-01-30 · Elad Hazan, Edgar Minasyan

In many online learning problems the computational bottleneck for gradient-based methods is the projection operation. For this reason, in many problems the most efficient algorithms are based on the Frank-Wolfe method, w…