Please use this identifier to cite or link to this item: http://arks.princeton.edu/ark:/88435/dsp01ns064873t
 Title: Estimation Error For Regression and Optimal Convergence Rate Authors: Wang, Yao Advisors: E, Weinan Contributors: Mathematics Department Subjects: Applied mathematics Issue Date: 2018 Publisher: Princeton, NJ : Princeton University Abstract: In this thesis, we study the optimal convergence rate for the universal estimation error. Let F be the excess loss class associated with the hypothesis space and n be the size of the data set, we prove that if the Fat-shattering dimension satisfies fat(F) = O(n^p), then the universal estimation error is of O(n^{1/2}) for p < 2 and O(n^{1/p}) for p > 2. Among other things, this result gives a criterion for a hypothesis class to achieve the minmax optimal rate of O(n^{1/2}). Examples are also provided for optimal rates not equal to O(n^{1/p}), such as compact supported convex Lipschitz continuous functions in Rd with d > 4 with optimal rate approximately about O(n^{2/d}). Training in practice may only explore a certain subspace in F. It is useful to bound the complexity of the subspace explored instead of the whole F. This is done for the gradient descent method. URI: http://arks.princeton.edu/ark:/88435/dsp01ns064873t Alternate format: The Mudd Manuscript Library retains one bound copy of each dissertation. Search for these copies in the library's main catalog: catalog.princeton.edu Type of Material: Academic dissertations (Ph.D.) Language: en Appears in Collections: Mathematics

Files in This Item:
File Description SizeFormat