中文
相关论文

相关论文: Stochastic Frank-Wolfe: Unified Analysis and Zoo o…

200 篇论文

In this paper, we consider the general non-oblivious stochastic optimization where the underlying stochasticity may change during the optimization procedure and depends on the point at which the function is evaluated. We develop Stochastic…

最优化与控制 · 数学 2020-09-10 Hamed Hassani , Amin Karbasi , Aryan Mokhtari , Zebang Shen

Deep neural networks is today one of the most popular choices in classification, regression and function approximation. However, the training of such deep networks is far from trivial as there are often millions of parameters to tune.…

机器学习 · 计算机科学 2020-06-09 Jakob Stigenberg

The Frank-Wolfe algorithm is a classic method for constrained optimization problems. It has recently been popular in many machine learning applications because its projection-free property leads to more efficient iterations. In this paper,…

最优化与控制 · 数学 2020-10-23 Cheng Chen , Luo Luo , Weinan Zhang , Yong Yu

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

This article deals with multiobjective composite optimization problems that consist of simultaneously minimizing several objective functions, each of which is composed of a combination of smooth and non-smooth functions. To tackle these…

最优化与控制 · 数学 2023-02-28 P. B. Assunção , O. P. Ferreira , L. F. Prudente

One of the beauties of the projected gradient descent method lies in its rather simple mechanism and yet stable behavior with inexact, stochastic gradients, which has led to its wide-spread use in many machine learning applications.…

最优化与控制 · 数学 2019-10-11 Mingrui Zhang , Zebang Shen , Aryan Mokhtari , Hamed Hassani , Amin Karbasi

In this paper we provide an introduction to the Frank-Wolfe algorithm, a method for smooth convex optimization in the presence of (relatively) complicated constraints. We will present the algorithm, introduce key concepts, and establish…

最优化与控制 · 数学 2023-11-30 Sebastian Pokutta

Frank-Wolfe (FW) algorithms have been often proposed over the last few years as efficient solvers for a variety of optimization problems arising in the field of Machine Learning. The ability to work with cheap projection-free iterations and…

Frank-Wolfe algorithms for convex minimization have recently gained considerable attention from the Optimization and Machine Learning communities, as their properties make them a suitable choice in a variety of applications. However, as…

机器学习 · 统计学 2015-10-27 Emanuele Frandi , Ricardo Nanculef , Johan Suykens

This paper studies the empirical efficacy and benefits of using projection-free first-order methods in the form of Conditional Gradients, a.k.a. Frank-Wolfe methods, for training Neural Networks with constrained parameters. We draw…

机器学习 · 计算机科学 2020-10-22 Sebastian Pokutta , Christoph Spiegel , Max Zimmer

We propose a novel generalization of the conditional gradient (CG / Frank-Wolfe) algorithm for minimizing a smooth function $f$ under an intersection of compact convex sets, using a first-order oracle for $\nabla f$ and linear minimization…

最优化与控制 · 数学 2024-10-11 Zev Woodstock , Sebastian Pokutta

Recently, there has been a renewed interest in the machine learning community for variants of a sparse greedy approximation procedure for concave optimization known as {the Frank-Wolfe (FW) method}. In particular, this procedure has been…

计算机视觉与模式识别 · 计算机科学 2015-10-27 Hector Allende , Emanuele Frandi , Ricardo Nanculef , Claudio Sartori

We study the convergence properties of the original and away-step Frank-Wolfe algorithms for linearly constrained stochastic optimization assuming the availability of unbiased objective function gradient estimates. The objective function is…

最优化与控制 · 数学 2025-04-08 Natthawut Boonsiriphatthanajaroen , Shane G. Henderson

The Frank-Wolfe method (a.k.a. conditional gradient algorithm) for smooth optimization has regained much interest in recent years in the context of large scale optimization and machine learning. A key advantage of the method is that it…

最优化与控制 · 数学 2015-08-17 Dan Garber , Elad Hazan

We present a blended conditional gradient approach for minimizing a smooth convex function over a polytope P, combining the Frank--Wolfe algorithm (also called conditional gradient) with gradient-based steps, different from away steps and…

最优化与控制 · 数学 2025-03-24 Gábor Braun , Sebastian Pokutta , Dan Tu , Stephen Wright

In this paper, we propose a generalized conditional gradient method for multiobjective optimization, which can be viewed as an improved extension of the classical Frank-Wolfe (conditional gradient) method for single-objective optimization.…

最优化与控制 · 数学 2025-03-25 Anteneh Getachew Gebrie , Ellen Hidemi Fukuda

We introduce a new class of Frank-Wolfe algorithms for minimizing differentiable functionals over probability measures. This framework can be shown to encompass a diverse range of tasks in areas such as artificial intelligence,…

统计计算 · 统计学 2021-05-13 Carson Kent , Jose Blanchet , Peter Glynn

The analysis of Frank Wolfe (FW) variants is often complicated by the presence of different kinds of "good" and "bad" steps. In this article we aim to simplify the convergence analysis of some of these variants by getting rid of such a…

最优化与控制 · 数学 2022-11-22 Francesco Rinaldi , Damiano Zeffiro

We present new results for the Frank-Wolfe method (also known as the conditional gradient method). We derive computational guarantees for arbitrary step-size sequences, which are then applied to various step-size rules, including simple…

最优化与控制 · 数学 2014-06-03 Robert M. Freund , Paul Grigas

The Frank-Wolfe method solves smooth constrained convex optimization problems at a generic sublinear rate of $\mathcal{O}(1/T)$, and it (or its variants) enjoys accelerated convergence rates for two fundamental classes of constraints:…

最优化与控制 · 数学 2020-06-17 Thomas Kerdreux , Alexandre d'Aspremont , Sebastian Pokutta