To refer to this page use:
|Abstract:||We consider the problem of prediction with expert advice when the losses of the experts have low-dimensional structure: they are restricted to an unknown d-dimensional subspace. We devise algorithms with regret bounds that are independent of the number of experts and depend only on the rank d. For the stochastic model we show a tight bound of Θ(\sqrtdT), and extend it to a setting of an approximate d subspace. For the adversarial model we show an upper bound of O(d\sqrtT) and a lower bound of Ω(\sqrtdT).|
|Citation:||Hazan, Elad, Tomer Koren, Roi Livni, and Yishay Mansour. "Online Learning with Low Rank Experts." In Conference on Learning Theory (2016): pp. 1096-1114.|
|Pages:||1096 - 1114|
|Type of Material:||Conference Article|
|Journal/Proceeding Title:||Conference on Learning Theory|
|Version:||Final published version. Article is made available in OAR by the publisher's permission or policy.|
Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.