arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.03795cs.LGmath.OCstat.ML
收藏

随机约束凸极小化问题的条件梯度方法

Conditional gradient methods for stochastically constrained convex minimization

École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院)

Maria-Luiza Vladarean, Ahmet Alacaoglu, Ya-Ping Hsieh, Volkan Cevher

摘要:

提出了两种新的基于条件梯度的方法来求解具有大量线性约束的结构随机凸优化问题。这个模板的迭代自然产生于组合问题的SDP松弛,其涉及在问题维度上是多项式的许多约束。我们的框架的最重要的特点是,只有一个子集的约束处理在每次迭代,从而获得了计算优势,需要完整的通行证。我们的算法依赖于方差减少和平滑结合使用的条件梯度步骤,并伴随着严格的收敛保证。初步的数值实验说明了该方法的实际性能。

英文摘要:

We propose two novel conditional gradient-based methods for solving structured stochastic convex optimization problems with a large number of linear constraints. Instances of this template naturally arise from SDP-relaxations of combinatorial problems, which involve a number of constraints that is polynomial in the problem dimension. The most important feature of our framework is that only a subset of the constraints is processed at each iteration, thus gaining a computational advantage over prior works that require full passes. Our algorithms rely on variance reduction and smoothing used in conjunction with conditional gradient steps, and are accompanied by rigorous convergence guarantees. Preliminary numerical experiments are provided for illustrating the practical performance of the methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑