Optimal Probability Estimation with Applications to Prediction and Classification
Abstract
Via a unified viewpoint of probability estimation, classification,and prediction, we derive a uniformly-optimal combined-probability estimator, construct a classifier that uniformly approaches the error of the best possible label-invariant classifier, and improve existing results on pattern prediction and compression.
Cite
Text
Acharya et al. "Optimal Probability Estimation with Applications to Prediction and Classification." Annual Conference on Computational Learning Theory, 2013.Markdown
[Acharya et al. "Optimal Probability Estimation with Applications to Prediction and Classification." Annual Conference on Computational Learning Theory, 2013.](https://mlanthology.org/colt/2013/acharya2013colt-optimal/)BibTeX
@inproceedings{acharya2013colt-optimal,
title = {{Optimal Probability Estimation with Applications to Prediction and Classification}},
author = {Acharya, Jayadev and Jafarpour, Ashkan and Orlitsky, Alon and Suresh, Ananda Theertha},
booktitle = {Annual Conference on Computational Learning Theory},
year = {2013},
pages = {764-796},
url = {https://mlanthology.org/colt/2013/acharya2013colt-optimal/}
}