paper-with-me

홈 › Papers

Frank-Wolfe algorithm for learning SVM-type multi-category classifiers

2020-08-20 · Kenya Tajima, Yoshihiro Hirohashi, Esmeraldo Ronnie Rey Zara, Tsuyoshi Kato

Multi-category support vector machine (MC-SVM) is one of the most popular machine learning algorithms. There are lots of variants of MC-SVM, although different optimization algorithms were developed for different learning machines. In this study, we developed a new optimization algorithm that can be applied to many of MC-SVM variants. The algorithm is based on the Frank-Wolfe framework that requires two subproblems, direction finding and line search, in each iteration. The contribution of this study is the discovery that both subproblems have a closed form solution if the Frank-Wolfe framework is applied to the dual problem. Additionally, the closed form solutions on both for the direction finding and for the line search exist even for the Moreau envelopes of the loss functions. We use several large datasets to demonstrate that the proposed optimization algorithm converges rapidly and thereby improves the pattern recognition performance.

📄 PDF Abstract BibTeX arXiv:2008.08894

Code (0)

등록된 구현이 없습니다.

Tasks

Vocal Bursts Type Prediction

Similar Papers 제목 키워드 기반

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…

Linear Convergence of a Frank-Wolfe Type Algorithm over Trace-Norm Balls

2017-08-07 · NeurIPS 2017 12 · Zeyuan Allen-Zhu, Elad Hazan, Wei Hu, Yuanzhi Li

We propose a rank-$k$ variant of the classical Frank-Wolfe algorithm to solve convex optimization over a trace-norm ball. Our algorithm replaces the top singular-vector computation ($1$-SVD) in Frank-Wolfe with a top-$k$…

Optimized projection-free algorithms for online learning: construction and worst-case analysis

2025-06-06 · Julien Weibel, Pierre Gaillard, Wouter M. Koolen, Adrien Taylor

This work studies and develop projection-free algorithms for online learning with linear optimization oracles (a.k.a. Frank-Wolfe) for handling the constraint set. More precisely, this work (i) provides an improved (opti…

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 F…

Beyond Short Steps in Frank-Wolfe Algorithms

2025-01-30 · David Martínez-Rubio, Sebastian Pokutta

We introduce novel techniques to enhance Frank-Wolfe algorithms by leveraging function smoothness beyond traditional short steps. Our study focuses on Frank-Wolfe algorithms with step sizes that incorporate primal-dual g…