Alekh Agarwal, Dean P. Foster, Daniel Hsu, Sham M. Kakade, Alexander Rakhlin. Stochastic convex optimization with bandit feedback. In John Shawe-Taylor, Richard S. Zemel, Peter L. Bartlett, Fernando C. N. Pereira, Kilian Q. Weinberger, editors, Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, Granada, Spain. pages 1035-1043, 2011. [doi]
@inproceedings{AgarwalFHKR11, title = {Stochastic convex optimization with bandit feedback}, author = {Alekh Agarwal and Dean P. Foster and Daniel Hsu and Sham M. Kakade and Alexander Rakhlin}, year = {2011}, url = {http://books.nips.cc/papers/files/nips24/NIPS2011_0641.pdf}, researchr = {https://researchr.org/publication/AgarwalFHKR11}, cites = {0}, citedby = {0}, pages = {1035-1043}, booktitle = {Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, Granada, Spain}, editor = {John Shawe-Taylor and Richard S. Zemel and Peter L. Bartlett and Fernando C. N. Pereira and Kilian Q. Weinberger}, }