中文
相关论文

相关论文: Boosted Stochastic Frank-Wolfe for Constrained Non…

200 篇论文

We study Frank-Wolfe methods for nonconvex stochastic and finite-sum optimization problems. Frank-Wolfe methods (in the convex case) have gained tremendous recent interest in machine learning and optimization communities due to their…

最优化与控制 · 数学 2016-08-01 Sashank J. Reddi , Suvrit Sra , Barnabas Poczos , Alex Smola

The Frank-Wolfe optimization algorithm has recently regained popularity for machine learning applications due to its projection-free property and its ability to handle structured constraints. However, in the stochastic learning setting, it…

机器学习 · 计算机科学 2017-09-15 Elad Hazan , Haipeng Luo

In the present paper, we formulate two versions of Frank--Wolfe algorithm or conditional gradient method to solve the DC optimization problem with an adaptive step size. The DC objective function consists of two components; the first is…

最优化与控制 · 数学 2026-02-02 R. Díaz Millán , O. P. Ferreira , J. Ugon

This paper considers distributed stochastic optimization, in which a number of agents cooperate to optimize a global objective function through local computations and information exchanges with neighbors over a network. Stochastic…

最优化与控制 · 数学 2022-08-09 Jie Hou , Xianlin Zeng , Gang Wang , Jian Sun , Jie Chen

The Frank-Wolfe algorithm has become a popular first-order optimization algorithm for it is simple and projection-free, and it has been successfully applied to a variety of real-world problems. Its main drawback however lies in its…

最优化与控制 · 数学 2020-06-25 Cyrille W. Combettes , Sebastian Pokutta

We study the Frank-Wolfe algorithm for constrained optimization problems with relatively smooth objectives. Building upon our previous work, we propose a fully adaptive variant of the Frank-Wolfe method that dynamically adjusts the step…

最优化与控制 · 数学 2025-08-27 A. A. Vyguzov , F. S. Stonyakin

Frank-Wolfe methods are projection-free algorithms for constrained optimization whose practical performance often depends critically on the choice of step size. Classical closed-loop step-size rules typically require prior knowledge of a…

最优化与控制 · 数学 2026-05-29 Khanh-Hung Giang-Tran , Soroosh Shafiee , Nam Ho-Nguyen

We propose an enhanced zeroth-order stochastic Frank-Wolfe framework to address constrained finite-sum optimization problems, a structure prevalent in large-scale machine-learning applications. Our method introduces a novel double variance…

机器学习 · 计算机科学 2025-01-24 Haishan Ye , Yinghui Huang , Hao Di , Xiangyu Chang

The Conditional Gradient (or Frank-Wolfe) method is one of the most well-known methods for solving constrained optimization problems appearing in various machine learning tasks. The simplicity of iteration and applicability to many…

The stochastic Frank-Wolfe method has recently attracted much general interest in the context of optimization for statistical and machine learning due to its ability to work with a more general feasible region. However, there has been a…

最优化与控制 · 数学 2019-11-06 Haihao Lu , Robert M. Freund

The Frank-Wolfe algorithm, a very first optimization method and also known as the conditional gradient method, was introduced by Frank and Wolfe in 1956. Due to its simple linear subproblems, the Frank-Wolfe algorithm has recently been…

最优化与控制 · 数学 2017-10-23 Hong-Kun Xu

The Frank-Wolfe method and its extensions are well-suited for delivering solutions with desirable structural properties, such as sparsity or low-rank structure. We introduce a new variant of the Frank-Wolfe method that combines Frank-Wolfe…

最优化与控制 · 数学 2019-06-11 Paul Grigas , Alfonso Lobos , Nathan Vermeersch

Some variant of the Frank-Wolfe method for convex optimization problems with adaptive selection of the step parameter corresponding to information about the smoothness of the objective function (the Lipschitz constant of the gradient).…

最优化与控制 · 数学 2023-08-01 G. V. Aivazian , F. S. Stonyakin , D. A. Pasechnyuk , M. S. Alkousa , A. M. Raigorodskii

The complexity in large-scale optimization can lie in both handling the objective function and handling the constraint set. In this respect, stochastic Frank-Wolfe algorithms occupy a unique position as they alleviate both computational…

最优化与控制 · 数学 2021-02-16 Cyrille W. Combettes , Christoph Spiegel , Sebastian Pokutta

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. Specifically, we propose an…

最优化与控制 · 数学 2020-08-11 Feihu Huang , Lue Tao , Songcan Chen

We introduce a few variants on Frank-Wolfe style algorithms suitable for large scale optimization. We show how to modify the standard Frank-Wolfe algorithm using stochastic gradients, approximate subproblem solutions, and sketched decision…

最优化与控制 · 数学 2018-08-17 Lijun Ding , Madeleine Udell

This paper considers stochastic convex optimization problems with two sets of constraints: (a) deterministic constraints on the domain of the optimization variable, which are difficult to project onto; and (b) deterministic or stochastic…

最优化与控制 · 数学 2022-05-25 Zeeshan Akhtar , Ketan Rajawat

We propose Frank--Wolfe (FW) algorithms with an adaptive Bregman step-size strategy for smooth adaptable (also called: relatively smooth) (weakly-) convex functions. This means that the gradient of the objective function is not necessarily…

最优化与控制 · 数学 2026-02-19 Shota Takahashi , Sebastian Pokutta , Akiko Takeda

We propose a randomized block-coordinate variant of the classic Frank-Wolfe algorithm for convex optimization with block-separable constraints. Despite its lower iteration cost, we show that it achieves a similar convergence rate in duality…

机器学习 · 计算机科学 2013-01-15 Simon Lacoste-Julien , Martin Jaggi , Mark Schmidt , Patrick Pletscher

We propose a semi-stochastic Frank-Wolfe algorithm with away-steps for regularized empirical risk minimization and extend it to problems with block-coordinate structure. Our algorithms use adaptive step-size and we show that they converge…

最优化与控制 · 数学 2016-02-16 Donald Goldfarb , Garud Iyengar , Chaoxu Zhou
‹ 上一页 1 2 3 10 下一页 ›