Math @ Duke

Publications [#320927] of Mauro Maggioni
Papers Published
 Liao, W; Maggioni, M; Vigogna, S, Learning adaptive multiscale approximations to data and functions near lowdimensional sets,
2016 IEEE Information Theory Workshop, ITW 2016
(October, 2016),
pp. 226230, ISBN 9781509010905 [doi]
(last updated on 2018/07/17)
Abstract: © 2016 IEEE. In the setting where a data set in D consists of samples from a probability measure ρ concentrated on or near an unknown ddimensional set M, with D large but d ≪ D, we consider two sets of problems: geometric approximation of M and regression of a function on M. In the first case we construct multiscale lowdimensional empirical approximations ofM, which are adaptive whenMhas geometric regularity that may vary at different locations and scales, and give performance guarantees. In the second case we exploit these empirical geometric approximations to construct multiscale approximations to on M, which adapt to the unknown regularity of even when this varies at different scales and locations. We prove guarantees showing that we attain the same learning rates as if was defined on a Euclidean domain of dimension d, instead of an unknown manifold M. All algorithms have complexity O(n log n), with constants scaling linearly in D and exponentially in d.


dept@math.duke.edu
ph: 919.660.2800
fax: 919.660.2821
 
Mathematics Department
Duke University, Box 90320
Durham, NC 277080320

