Strongly Adaptive Online Learning

Amit Daniely, Alon Gonen, Shai Shalev-Shwartz
Proceedings of the 32nd International Conference on Machine Learning, PMLR 37:1405-1411, 2015.

Abstract

Strongly adaptive algorithms are algorithms whose performance on every time interval is close to optimal. We present a reduction that can transform standard low-regret algorithms to strongly adaptive. As a consequence, we derive simple, yet efficient, strongly adaptive algorithms for a handful of problems.

Cite this Paper

BibTeX
@InProceedings{pmlr-v37-daniely15, title = {Strongly Adaptive Online Learning}, author = {Daniely, Amit and Gonen, Alon and Shalev-Shwartz, Shai}, booktitle = {Proceedings of the 32nd International Conference on Machine Learning}, pages = {1405--1411}, year = {2015}, editor = {Bach, Francis and Blei, David}, volume = {37}, series = {Proceedings of Machine Learning Research}, address = {Lille, France}, month = {07--09 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v37/daniely15.pdf}, url = {https://proceedings.mlr.press/v37/daniely15.html}, abstract = {Strongly adaptive algorithms are algorithms whose performance on every time interval is close to optimal. We present a reduction that can transform standard low-regret algorithms to strongly adaptive. As a consequence, we derive simple, yet efficient, strongly adaptive algorithms for a handful of problems.} }
Endnote
%0 Conference Paper %T Strongly Adaptive Online Learning %A Amit Daniely %A Alon Gonen %A Shai Shalev-Shwartz %B Proceedings of the 32nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2015 %E Francis Bach %E David Blei %F pmlr-v37-daniely15 %I PMLR %P 1405--1411 %U https://proceedings.mlr.press/v37/daniely15.html %V 37 %X Strongly adaptive algorithms are algorithms whose performance on every time interval is close to optimal. We present a reduction that can transform standard low-regret algorithms to strongly adaptive. As a consequence, we derive simple, yet efficient, strongly adaptive algorithms for a handful of problems.
RIS
TY - CPAPER TI - Strongly Adaptive Online Learning AU - Amit Daniely AU - Alon Gonen AU - Shai Shalev-Shwartz BT - Proceedings of the 32nd International Conference on Machine Learning DA - 2015/06/01 ED - Francis Bach ED - David Blei ID - pmlr-v37-daniely15 PB - PMLR DP - Proceedings of Machine Learning Research VL - 37 SP - 1405 EP - 1411 L1 - http://proceedings.mlr.press/v37/daniely15.pdf UR - https://proceedings.mlr.press/v37/daniely15.html AB - Strongly adaptive algorithms are algorithms whose performance on every time interval is close to optimal. We present a reduction that can transform standard low-regret algorithms to strongly adaptive. As a consequence, we derive simple, yet efficient, strongly adaptive algorithms for a handful of problems. ER -
APA
Daniely, A., Gonen, A. & Shalev-Shwartz, S.. (2015). Strongly Adaptive Online Learning. Proceedings of the 32nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 37:1405-1411 Available from https://proceedings.mlr.press/v37/daniely15.html.

Related Material