Towards Minimax Policies for Online Linear Optimization with Bandit Feedback. Bubeck, S., Cesa-Bianchi, N., & Kakade, S. In Shie, M., Srebro, N., & Williamson, R., editors, Proceedings of the 25th Annual Conference on Learning Theory (COLT), volume PMLR 23, pages 41.1–41.14, 2012.
![Towards Minimax Policies for Online Linear Optimization with Bandit Feedback [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper bibtex
Paper bibtex @inproceedings{2012bubecltowards,
title={Towards Minimax Policies for Online Linear Optimization with Bandit Feedback},
author={Bubeck, S{\'e}bastien and Cesa-Bianchi, Nicolo and Kakade, Sham},
booktitle={Proceedings of the 25th Annual Conference on Learning Theory (COLT)},
volume={PMLR 23},
pages={41.1--41.14},
year={2012},
editor={Mannor Shie and Srebro, Nathan and Williamson, Robert},
%http://proceedings.mlr.press/v23/bubeck12a.html
url_Paper={https://arxiv.org/pdf/1202.3079.pdf}
}Downloads: 0
{"_id":"XgYXSRjZ4d6mKgGmt","bibbaseid":"bubeck-cesabianchi-kakade-towardsminimaxpoliciesforonlinelinearoptimizationwithbanditfeedback-2012","authorIDs":["3AvMzPYKCwJ47GDa9","EHMXLrfGuoBWJma4Y","LggRPMQ9gYftaaitv","Z6Duw9GRvyRSY5HoX","aCideRtgMzdYSNQLG","nmmAcRWAsCMNA5DWa","pMxxicnBGZfB4wmW7","qE8E2QsF2nJsQCvyo","tDcgcQ2rQBSi5fSMC","wvLJWtBn62aGEAczQ","x5GySF8B9B99de7CM"],"author_short":["Bubeck, S.","Cesa-Bianchi, N.","Kakade, S."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Towards Minimax Policies for Online Linear Optimization with Bandit Feedback","author":[{"propositions":[],"lastnames":["Bubeck"],"firstnames":["Sébastien"],"suffixes":[]},{"propositions":[],"lastnames":["Cesa-Bianchi"],"firstnames":["Nicolo"],"suffixes":[]},{"propositions":[],"lastnames":["Kakade"],"firstnames":["Sham"],"suffixes":[]}],"booktitle":"Proceedings of the 25th Annual Conference on Learning Theory (COLT)","volume":"PMLR 23","pages":"41.1–41.14","year":"2012","editor":[{"firstnames":["Mannor"],"propositions":[],"lastnames":["Shie"],"suffixes":[]},{"propositions":[],"lastnames":["Srebro"],"firstnames":["Nathan"],"suffixes":[]},{"propositions":[],"lastnames":["Williamson"],"firstnames":["Robert"],"suffixes":[]}],"url_paper":"https://arxiv.org/pdf/1202.3079.pdf","bibtex":"@inproceedings{2012bubecltowards,\n title={Towards Minimax Policies for Online Linear Optimization with Bandit Feedback},\n author={Bubeck, S{\\'e}bastien and Cesa-Bianchi, Nicolo and Kakade, Sham},\n booktitle={Proceedings of the 25th Annual Conference on Learning Theory (COLT)},\n volume={PMLR 23},\n pages={41.1--41.14},\n year={2012},\n editor={Mannor Shie and Srebro, Nathan and Williamson, Robert},\n %http://proceedings.mlr.press/v23/bubeck12a.html\n url_Paper={https://arxiv.org/pdf/1202.3079.pdf}\n}\n\n","author_short":["Bubeck, S.","Cesa-Bianchi, N.","Kakade, S."],"editor_short":["Shie, M.","Srebro, N.","Williamson, R."],"key":"2012bubecltowards-1","id":"2012bubecltowards-1","bibbaseid":"bubeck-cesabianchi-kakade-towardsminimaxpoliciesforonlinelinearoptimizationwithbanditfeedback-2012","role":"author","urls":{" paper":"https://arxiv.org/pdf/1202.3079.pdf"},"metadata":{"authorlinks":{"srebro, n":"https://nati.ttic.edu/research.html"}},"downloads":0},"bibtype":"inproceedings","biburl":"natisb.github.io/Pub.bib","creationDate":"2020-06-22T00:52:05.809Z","downloads":0,"keywords":[],"search_terms":["towards","minimax","policies","online","linear","optimization","bandit","feedback","bubeck","cesa-bianchi","kakade"],"title":"Towards Minimax Policies for Online Linear Optimization with Bandit Feedback","year":2012,"dataSources":["MKpBoHoD8jbmsQitE","gXDHDS9LFkGrW59EE","RQcQjmmjQdZFcGmkL","d2cjLLaXdKBg4GZbu"]}