Anytime Representation Learning
Abstract
Evaluation cost during test-time is becoming increasingly important as many real-world applications need fast evaluation (e.g. web search engines, email spam filtering) or use expensive features (e.g. medical diagnosis). We introduce Anytime Feature Representations (AFR), a novel algorithm that explicitly addresses this trade-off in the data representation rather than in the classifier. This enables us to turn conventional classifiers, in particular Support Vector Machines, into test-time cost sensitive anytime classifiers - combining the advantages of anytime learning and large-margin classification.
Cite
Text
Xu et al. "Anytime Representation Learning." International Conference on Machine Learning, 2013.Markdown
[Xu et al. "Anytime Representation Learning." International Conference on Machine Learning, 2013.](https://mlanthology.org/icml/2013/xu2013icml-anytime/)BibTeX
@inproceedings{xu2013icml-anytime,
title = {{Anytime Representation Learning}},
author = {Xu, Zhixiang and Kusner, Matt and Huang, Gao and Weinberger, Kilian},
booktitle = {International Conference on Machine Learning},
year = {2013},
pages = {1076-1084},
volume = {28},
url = {https://mlanthology.org/icml/2013/xu2013icml-anytime/}
}