Learning Reductions That Really Work This paper summarizes the mathematical and computational techniques that have enabled learning reductions to effectively address a wide class of tasks.

作者： Alina Beygelzimer , Hal Daume , Paul Mineiro , John Langford

DOI:

关键词: Machine learning 、 Computational learning theory 、 Class (computer programming) 、 Multi-task learning 、 Algorithmic learning theory 、 Work (electrical) 、 Computer science 、 Artificial intelligence

摘要: In this paper, we provide a summary of the mathematical and computational techniques that have enabled learning reductions to effectively address wide class tasks, show approach solving machine problems can be broadly useful. Our work is instantiated tested in library, Vowpal Wabbit, prove discussed here are fully viable practice.

暂无可下载资源，当前可以选择系统获取到有开放资源时通知我或者直接发起求助文献求助

参考文章(62)

Bianca Zadrozny, Alina Beygelzimer, John Langford, Weighted one-against-all national conference on artificial intelligence. pp. 720- 725 ,(2005)

Bianca Zadrozny, Charles P. Elkan, Policy mining: learning decision policies from fixed sets of data University of California, San Diego. ,(2003)

Oscar Beijbom, Mohammad Saberian, Nuno Vasconcelos, David Kriegman, Guess-Averse Loss Functions For Cost-Sensitive Multiclass Boosting international conference on machine learning. pp. 586- 594 ,(2014)

John Langford, Robust Efficient Conditional Probability Estimation. conference on learning theory. pp. 316- 317 ,(2010)

Kai-Wei Chang, Vivek Srikumar, Dan Roth, Multi-core structural SVM training european conference on machine learning. pp. 401- 416 ,(2013) , 10.1007/978-3-642-40991-2_26

Yuehua Xu, Alan Fern, Sungwook Yoon, Discriminative learning of beam-search heuristics for planning international joint conference on artificial intelligence. pp. 2041- 2046 ,(2007)

Liang Huang, Suphan Fayong, Yang Guo, Structured Perceptron with Inexact Search north american chapter of the association for computational linguistics. pp. 142- 151 ,(2012)

Alina Beygelzimer, John Langford, Daniel J. Hsu, Zhang Tong, Agnostic Active Learning Without Constraints neural information processing systems. ,vol. 23, pp. 199- 207 ,(2010)

John Langford, Alina Beygelzimer, Sensitive error correcting output codes conference on learning theory. pp. 158- 172 ,(2005) , 10.1007/11503415_11

10.

T. G. Dietterich, G. Bakiri, Solving multiclass learning problems via error-correcting output codes Journal of Artificial Intelligence Research. ,vol. 2, pp. 263- 286 ,(1994) , 10.1613/JAIR.105

Learning Reductions That Really Work This paper summarizes the mathematical and computational techniques that have enabled learning reductions to effectively address a wide class of tasks.

来源期刊

我的账户

Learning Reductions That Really Work This paper summarizes the mathematical and computational techniques that have enabled learning reductions to effectively address a wide class of tasks.

来源期刊

相似文章 0

我的账户