arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1009.0571stat.MLcs.SYeess.SYmath.OC
收藏

随机凸优化的预言机复杂度的信息论下界

Information-theoretic lower bounds on the oracle complexity of stochastic convex optimization

UC Berkeley(加州大学伯克利分校);UT Austin(德克萨斯大学奥斯汀分校);QUT, Brisbane, Australia(昆士兰科技大学)

Alekh Agarwal, Peter L. Bartlett, Pradeep Ravikumar, Martin J. Wainwright

AI总结:

本文通过信息论方法,在预言机计算模型下研究了随机凸优化的复杂度,改进了已知结果并获得了多种函数类的紧极小极大复杂度估计。

摘要:

相对于关于凸优化复杂度上界的大量文献,这些问题的基本难度受到的关注较少。鉴于凸优化在机器学习和统计学中的广泛应用,理解这些复杂度理论问题非常重要。在本文中,我们在预言机计算模型下研究随机凸优化的复杂度。我们改进了已知结果,并获得了各种函数类的紧极小极大复杂度估计。

英文摘要:

Relative to the large literature on upper bounds on complexity of convex optimization, lesser attention has been paid to the fundamental hardness of these problems. Given the extensive use of convex optimization in machine learning and statistics, gaining an understanding of these complexity-theoretic issues is important. In this paper, we study the complexity of stochastic convex optimization in an oracle model of computation. We improve upon known results and obtain tight minimax complexity estimates for various function classes.

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。

↑