Optimal Probability Estimation with Applications to Prediction and Classification

Jayadev Acharya, Ashkan Jafarpour, Alon Orlitsky, Ananda Theertha Suresh
Proceedings of the 26th Annual Conference on Learning Theory, PMLR 30:764-796, 2013.

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 this Paper

BibTeX
@InProceedings{pmlr-v30-Acharya13, title = {Optimal Probability Estimation with Applications to Prediction and Classification}, author = {Acharya, Jayadev and Jafarpour, Ashkan and Orlitsky, Alon and Suresh, Ananda Theertha}, booktitle = {Proceedings of the 26th Annual Conference on Learning Theory}, pages = {764--796}, year = {2013}, editor = {Shalev-Shwartz, Shai and Steinwart, Ingo}, volume = {30}, series = {Proceedings of Machine Learning Research}, address = {Princeton, NJ, USA}, month = {12--14 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v30/Acharya13.pdf}, url = {https://proceedings.mlr.press/v30/Acharya13.html}, 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.} }
Endnote
%0 Conference Paper %T Optimal Probability Estimation with Applications to Prediction and Classification %A Jayadev Acharya %A Ashkan Jafarpour %A Alon Orlitsky %A Ananda Theertha Suresh %B Proceedings of the 26th Annual Conference on Learning Theory %C Proceedings of Machine Learning Research %D 2013 %E Shai Shalev-Shwartz %E Ingo Steinwart %F pmlr-v30-Acharya13 %I PMLR %P 764--796 %U https://proceedings.mlr.press/v30/Acharya13.html %V 30 %X 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.
RIS
TY - CPAPER TI - Optimal Probability Estimation with Applications to Prediction and Classification AU - Jayadev Acharya AU - Ashkan Jafarpour AU - Alon Orlitsky AU - Ananda Theertha Suresh BT - Proceedings of the 26th Annual Conference on Learning Theory DA - 2013/06/13 ED - Shai Shalev-Shwartz ED - Ingo Steinwart ID - pmlr-v30-Acharya13 PB - PMLR DP - Proceedings of Machine Learning Research VL - 30 SP - 764 EP - 796 L1 - http://proceedings.mlr.press/v30/Acharya13.pdf UR - https://proceedings.mlr.press/v30/Acharya13.html AB - 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. ER -
APA
Acharya, J., Jafarpour, A., Orlitsky, A. & Suresh, A.T.. (2013). Optimal Probability Estimation with Applications to Prediction and Classification. Proceedings of the 26th Annual Conference on Learning Theory, in Proceedings of Machine Learning Research 30:764-796 Available from https://proceedings.mlr.press/v30/Acharya13.html.

Related Material