Dictionary Learning and Non-Asymptotic Bounds for Geometric Multi-Resolution Analysis |
| |
Authors: | Mauro Maggioni Stanislav Minsker Nate Strawn |
| |
Institution: | 1. Department of Mathematics, Duke University, N.C.
Duke Department of Electrical and Computer Engineering
Duke Department of Computer Science;2. Department of Mathematics, Duke University, N.C.
Duke Department of Statistical Sciences;3. Department of Mathematics, Duke University, N.C. |
| |
Abstract: | Data sets in high-dimensional spaces are often concentrated near low-dimensional sets. Geometric Multi-Resolution Analysis (Allard, Chen, Maggioni, 2012) was introduced as a method for approximating (in a robust, multiscale fashion) a low-dimensional set around which data may concentrated and also providing dictionary for sparse representation of the data. Moreover, the procedure is very computationally efficient. We introduce an estimator for low-dimensional sets supporting the data constructed from the GMRA approximations. We exhibit (near optimal) finite sample bounds on its performance, and demonstrate the robustness of this estimator with respect to noise and model error. In particular, our results imply that, if the data is supported on a low-dimensional manifold, the proposed sparse representations result in an error which depends only on the intrinsic dimension of the manifold. (© 2014 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim) |
| |
Keywords: | |
|
|