Coresets, sparse greedy approximation, and the Frank-Wolfe algorithm

Author:

Clarkson Kenneth L.1

Affiliation:

1. IBM Almaden Research Center, San Jose, CA

Abstract

The problem of maximizing a concave function f(x) in the unit simplex Δ can be solved approximately by a simple greedy algorithm. For given k , the algorithm can find a point x ( k ) on a k -dimensional face of Δ, such that f ( x ( k ) f(x * ) − O (1/ k ). Here f ( x * ) is the maximum value of f in Δ, and the constant factor depends on f . This algorithm and analysis were known before, and related to problems of statistics and machine learning, such as boosting, regression, and density mixture estimation. In other work, coming from computational geometry, the existence of ϵ-coresets was shown for the minimum enclosing ball problem by means of a simple greedy algorithm. Similar greedy algorithms, which are special cases of the Frank-Wolfe algorithm, were described for other enclosure problems. Here these results are tied together, stronger convergence results are reviewed, and several coreset bounds are generalized or strengthened.

Publisher

Association for Computing Machinery (ACM)

Subject

Mathematics (miscellaneous)

Reference45 articles.

1. Agarwal P. K. Har-Peled S. and Varadarajan K. R. 2005. Geometric approximation via coresets. In Combinatorial and Computational Geometry MSRI Publications Cambridge University Press 1--30. 2005. Agarwal P. K. Har-Peled S. and Varadarajan K. R. 2005. Geometric approximation via coresets. In Combinatorial and Computational Geometry MSRI Publications Cambridge University Press 1--30. 2005.

2. Ahipasaoglu D. Sun P. and Todd M. J. 2006. Linear convergence of a modified Frank-Wolfe algorithm for computing minimum volume ellipsoids. Tech. rep. 1452 Cornell University. Ahipasaoglu D. Sun P. and Todd M. J. 2006. Linear convergence of a modified Frank-Wolfe algorithm for computing minimum volume ellipsoids. Tech. rep. 1452 Cornell University.

3. Unifying Divergence Minimization and Statistical Inference Via Convex Duality

4. Computational discovery of gene modules and regulatory networks

5. Universal approximation bounds for superpositions of a sigmoidal function

Cited by 138 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Frank–Wolfe-type methods for a class of nonconvex inequality-constrained problems;Mathematical Programming;2024-02-03

2. Distributed Optimization With Projection-Free Dynamics: A Frank-Wolfe Perspective;IEEE Transactions on Cybernetics;2024-01

3. The Frank-Wolfe Algorithm: A Short Introduction;Jahresbericht der Deutschen Mathematiker-Vereinigung;2023-12-13

4. The Iterates of the Frank–Wolfe Algorithm May Not Converge;Mathematics of Operations Research;2023-12-07

5. Adaptive Variant of the Frank–Wolfe Algorithm for Convex Optimization Problems;Programming and Computer Software;2023-12

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3