arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.11079math.OC
收藏

仿射约束下强凸极小化的一个最优算法

An Optimal Algorithm for Strongly Convex Minimization under Affine Constraints

Adil Salim, Laurent Condat, Dmitry Kovalev, Peter Richtárik

摘要:

仿射约束下的最优化问题出现在机器学习的各个领域。我们考虑在仿射约束Kx=b下最小化光滑强凸函数F(x)的问题,并给出了F的梯度和乘K及其转置的计算.我们提供了梯度计算和矩阵乘法数量的下界,以实现给定的准确度。然后,我们提出了一个加速的原始对偶法实现这些下界。我们的算法是这类问题的第一个最优算法。

英文摘要:

Optimization problems under affine constraints appear in various areas of machine learning. We consider the task of minimizing a smooth strongly convex function F(x) under the affine constraint Kx=b, with an oracle providing evaluations of the gradient of F and multiplications by K and its transpose. We provide lower bounds on the number of gradient computations and matrix multiplications to achieve a given accuracy. Then we propose an accelerated primal-dual algorithm achieving these lower bounds. Our algorithm is the first optimal algorithm for this class of problems.

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。

↑