Communication Efficient Distributed Agnostic Boosting

Shang-Tse Chen, Maria-Florina Balcan, Duen Horng Chau
Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, PMLR 51:1299-1307, 2016.

Abstract

We consider the problem of learning from distributed data in the agnostic setting, i.e., in the presence of arbitrary forms of noise. Our main contribution is a general distributed boosting-based procedure for learning an arbitrary concept space, that is simultaneously noise tolerant, communication efficient, and computationally efficient. This improves significantly over prior works that were either communication efficient only in noise-free scenarios or computationally prohibitive. Empirical results on large synthetic and real-world datasets demonstrate the effectiveness and scalability of the proposed approach.

Cite this Paper

BibTeX
@InProceedings{pmlr-v51-chen16e, title = {Communication Efficient Distributed Agnostic Boosting}, author = {Chen, Shang-Tse and Balcan, Maria-Florina and Chau, Duen Horng}, booktitle = {Proceedings of the 19th International Conference on Artificial Intelligence and Statistics}, pages = {1299--1307}, year = {2016}, editor = {Gretton, Arthur and Robert, Christian C.}, volume = {51}, series = {Proceedings of Machine Learning Research}, address = {Cadiz, Spain}, month = {09--11 May}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v51/chen16e.pdf}, url = {https://proceedings.mlr.press/v51/chen16e.html}, abstract = {We consider the problem of learning from distributed data in the agnostic setting, i.e., in the presence of arbitrary forms of noise. Our main contribution is a general distributed boosting-based procedure for learning an arbitrary concept space, that is simultaneously noise tolerant, communication efficient, and computationally efficient. This improves significantly over prior works that were either communication efficient only in noise-free scenarios or computationally prohibitive. Empirical results on large synthetic and real-world datasets demonstrate the effectiveness and scalability of the proposed approach.} }
Endnote
%0 Conference Paper %T Communication Efficient Distributed Agnostic Boosting %A Shang-Tse Chen %A Maria-Florina Balcan %A Duen Horng Chau %B Proceedings of the 19th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2016 %E Arthur Gretton %E Christian C. Robert %F pmlr-v51-chen16e %I PMLR %P 1299--1307 %U https://proceedings.mlr.press/v51/chen16e.html %V 51 %X We consider the problem of learning from distributed data in the agnostic setting, i.e., in the presence of arbitrary forms of noise. Our main contribution is a general distributed boosting-based procedure for learning an arbitrary concept space, that is simultaneously noise tolerant, communication efficient, and computationally efficient. This improves significantly over prior works that were either communication efficient only in noise-free scenarios or computationally prohibitive. Empirical results on large synthetic and real-world datasets demonstrate the effectiveness and scalability of the proposed approach.
RIS
TY - CPAPER TI - Communication Efficient Distributed Agnostic Boosting AU - Shang-Tse Chen AU - Maria-Florina Balcan AU - Duen Horng Chau BT - Proceedings of the 19th International Conference on Artificial Intelligence and Statistics DA - 2016/05/02 ED - Arthur Gretton ED - Christian C. Robert ID - pmlr-v51-chen16e PB - PMLR DP - Proceedings of Machine Learning Research VL - 51 SP - 1299 EP - 1307 L1 - http://proceedings.mlr.press/v51/chen16e.pdf UR - https://proceedings.mlr.press/v51/chen16e.html AB - We consider the problem of learning from distributed data in the agnostic setting, i.e., in the presence of arbitrary forms of noise. Our main contribution is a general distributed boosting-based procedure for learning an arbitrary concept space, that is simultaneously noise tolerant, communication efficient, and computationally efficient. This improves significantly over prior works that were either communication efficient only in noise-free scenarios or computationally prohibitive. Empirical results on large synthetic and real-world datasets demonstrate the effectiveness and scalability of the proposed approach. ER -
APA
Chen, S., Balcan, M. & Chau, D.H.. (2016). Communication Efficient Distributed Agnostic Boosting. Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 51:1299-1307 Available from https://proceedings.mlr.press/v51/chen16e.html.

Related Material