Philip M. Long. New bounds on the price of bandit feedback for mistake-bounded online multiclass learning. In International Conference on Algorithmic Learning Theory, ALT 2017, 15-17 October 2017, Kyoto University, Kyoto, Japan. Volume 76 of Proceedings of Machine Learning Research, pages 3-10, PMLR, 2017. [doi]
@inproceedings{Long17-8, title = {New bounds on the price of bandit feedback for mistake-bounded online multiclass learning}, author = {Philip M. Long}, year = {2017}, url = {http://proceedings.mlr.press/v76/long17a.html}, researchr = {https://researchr.org/publication/Long17-8}, cites = {0}, citedby = {0}, pages = {3-10}, booktitle = {International Conference on Algorithmic Learning Theory, ALT 2017, 15-17 October 2017, Kyoto University, Kyoto, Japan}, volume = {76}, series = {Proceedings of Machine Learning Research}, publisher = {PMLR}, }