Data-driven algorithm design

Data-driven algorithm design
复制标题

数据驱动的算法设计

DOI:
10.1145/3394625
复制
发表时间:
2020
影响因子:
22.7
通讯作者:
Roughgarden, Tim
Roughgarden, Tim
中科院分区:
计算机科学3区
文献类型:
--
作者:
Gupta, Rishi;Roughgarden, Tim

文献摘要

参考文献

被引文献

相似文献

计算问题的最佳算法通常取决于“相关输入”,这是一个依赖于应用领域的概念,通常与形式表达不符。虽然有大量的文献的经验方法来选择最好的算法,为一个给定的应用领域,有令人惊讶的是很少的理论分析的problem.We模型的问题,确定一个好的算法从数据作为一个统计学习问题。我们的框架捕获了几个国家的最先进的经验和理论方法的问题,我们的研究结果确定的条件下,这些方法保证表现良好。我们解释我们的研究结果的背景下,学习贪婪算法,实例特征为基础的算法选择,并在机器学习中的参数调整。
The best algorithm for a computational problem generally depends on the "relevant inputs," a concept that depends on the application domain and often defies formal articulation. Although there is a large literature on empirical approaches to selecting the best algorithm for a given application domain, there has been surprisingly little theoretical analysis of the problem.We model the problem of identifying a good algorithm from data as a statistical learning problem. Our framework captures several state-of-the-art empirical and theoretical approaches to the problem, and our results identify conditions under which these approaches are guaranteed to perform well. We interpret our results in the contexts of learning greedy heuristics, instance feature-based algorithm selection, and parameter tuning in machine learning.
无线电频谱重新分配的经济学和计算机科学
DOI: 10.1073/pnas.1701997114
发表时间: 2017
期刊: Proceedings of the National Academy of Sciences
影响因子: --
作者:
Kevin Leyton;Paul R. Milgrom;I. Segal
通讯作者: I. Segal
DOI: 10.1016/j.artint.2013.10.003
发表时间: 2014-01-01
影响因子: 14.4
作者:
Hutter, Frank;Xu, Lin;Leyton-Brown, Kevin
通讯作者: Leyton-Brown, Kevin
用于特定应用算法选择的 PAC 方法
DOI: --
发表时间: 2015
期刊: SIAM journal on computing (Print)
影响因子: --
作者:
Rishi Gupta;Tim Roughgarden
通讯作者: Tim Roughgarden
DOI: 10.48550/arxiv.1611.04535
发表时间: 2016
期刊: arXiv e-prints
影响因子: --
作者:
Balcan Maria-Florina
通讯作者: Balcan Maria-Florina
DOI: --
发表时间: 2015
期刊: Neural Information Processing Systems
影响因子: --
作者:
Jamie Morgenstern;Tim Roughgarden
通讯作者: Tim Roughgarden