paper-with-me

홈 › Papers

How Does Momentum Help Frank Wolfe?

2020-06-19 · Bingcong Li, Mario Coutino, Georgios B. Giannakis, Geert Leus

We unveil the connections between Frank Wolfe (FW) type algorithms and the momentum in Accelerated Gradient Methods (AGM). On the negative side, these connections illustrate why momentum is unlikely to be effective for FW type algorithms. The encouraging message behind this link, on the other hand, is that momentum is useful for FW on a class of problems. In particular, we prove that a momentum variant of FW, that we term accelerated Frank Wolfe (AFW), converges with a faster rate $\tilde{\cal O}(\frac{1}{k^2})$ on certain constraint sets despite the same ${\cal O}(\frac{1}{k})$ rate as FW on general cases. Given the possible acceleration of AFW at almost no extra cost, it is thus a competitive alternative to FW. Numerical experiments on benchmarked machine learning tasks further validate our theoretical findings.

📄 PDF Abstract BibTeX arXiv:2006.11116

Code (0)

등록된 구현이 없습니다.

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…

A Multistep Frank-Wolfe Method

2022-10-14 · Zhaoyue Chen, Yifan Sun

The Frank-Wolfe algorithm has regained much interest in its use in structurally constrained machine learning applications. However, one major limitation of the Frank-Wolfe algorithm is the slow local convergence property…

Projection-Free CNN Pruning via Frank-Wolfe with Momentum: Sparser Models with Less Pretraining

2025-11-30 · Hamza ElMokhtar Shili, Natasha Patnaik, Isabelle Ruble, Kathryn Jarjoura 외 arxiv

We investigate algorithmic variants of the Frank-Wolfe (FW) optimization method for pruning convolutional neural networks. This is motivated by the "Lottery Ticket Hypothesis", which suggests the existence of smaller sub…

Image Classification

Stochastic Compositional Optimization via Hybrid Momentum Frank--Wolfe

2026-05-14 · El Mahdi Chayti arxiv

Stochastic compositional optimization minimizes objectives of the form $\min_{\bm{x} \in \mathcal{X}} F(\bm{f}(\bm{x}), \bm{x})$, where $\bm{f}$ is accessible only through noisy stochastic queries. Existing methods for t…

Accelerated Stochastic Gradient-free and Projection-free Methods

2020-07-16 · ICML 2020 1 · Feihu Huang, Lue Tao, Songcan Chen

In the paper, we propose a class of accelerated stochastic gradient-free and projection-free (a.k.a., zeroth-order Frank-Wolfe) methods to solve the constrained stochastic and finite-sum nonconvex optimization. Specifica…

Adversarial Attack