Estimation in high dimensions: a geometric perspective
R. Vershynin. (2014)cite arxiv:1405.5103v2.pdfComment: 56 pages, 9 figures. Multiple minor changes.
Abstract
This tutorial provides an exposition of a flexible geometric framework for
high dimensional estimation problems with constraints. The tutorial develops
geometric intuition about high dimensional sets, justifies it with some results
of asymptotic convex geometry, and demonstrates connections between geometric
results and estimation problems. The theory is illustrated with applications to
sparse recovery, matrix completion, quantization, linear and logistic
regression and generalized linear models.
%0 Generic
%1 vershynin2014estimation
%A Vershynin, Roman
%D 2014
%K acreuser optimization tutorial
%T Estimation in high dimensions: a geometric perspective
%U http://arxiv.org/abs/1405.5103
%X This tutorial provides an exposition of a flexible geometric framework for
high dimensional estimation problems with constraints. The tutorial develops
geometric intuition about high dimensional sets, justifies it with some results
of asymptotic convex geometry, and demonstrates connections between geometric
results and estimation problems. The theory is illustrated with applications to
sparse recovery, matrix completion, quantization, linear and logistic
regression and generalized linear models.
@misc{vershynin2014estimation,
abstract = {This tutorial provides an exposition of a flexible geometric framework for
high dimensional estimation problems with constraints. The tutorial develops
geometric intuition about high dimensional sets, justifies it with some results
of asymptotic convex geometry, and demonstrates connections between geometric
results and estimation problems. The theory is illustrated with applications to
sparse recovery, matrix completion, quantization, linear and logistic
regression and generalized linear models.},
added-at = {2016-04-28T06:45:06.000+0200},
author = {Vershynin, Roman},
biburl = {https://www.bibsonomy.org/bibtex/232a6110d1d7fd50caf59a30e622b07ce/pixor},
description = {1405.5103v2.pdf},
interhash = {0e5390732dde7c8fa1f474b0433ea2a5},
intrahash = {32a6110d1d7fd50caf59a30e622b07ce},
keywords = {acreuser optimization tutorial},
note = {cite arxiv:1405.5103v2.pdfComment: 56 pages, 9 figures. Multiple minor changes},
timestamp = {2016-04-28T06:45:06.000+0200},
title = {Estimation in high dimensions: a geometric perspective},
url = {http://arxiv.org/abs/1405.5103},
year = 2014
}