FoCM 2014 conference
Workshop C3 - Learning Theory
December 18, 14:30 ~ 15:00 - Room B23
A Tale of Three Regression Problems
Alexander Rakhlin
University of Pennsylvania, USA - rakhlin@wharton.upenn.edu
We consider the problem of regression in three scenarios: (a) random design under the assumption that the model F is correctly specified, (b) distribution-free statistical learning with respect to a reference class F; and (c) online regression with no assumption on the generative process. The first problem is often studied in the literature on nonparametric estimation, the second falls within the purview of statistical learning theory, and the third is studied within the online learning community. Do these three problems really differ from the minimax point of view? This question will be addressed in this talk.
Joint work with Karthik Sridharan (Cornell University) and Sasha Tsybakov (ENSAE-Paris Tech).