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
中科院分区:
文献类型:
--
作者:
Gupta, Rishi;Roughgarden, Tim
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.
登录
查看更多内容
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
影响因子:
14.4
作者:
Hutter, Frank;Xu, Lin;Leyton-Brown, Kevin
通讯作者:
Leyton-Brown, Kevin
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