The Dantzig selector for high dimensional statistical problems

Duration: 1 hour 8 mins 59 secs

Share this media item:

Embed this media item:

<iframe width="_width_" height="_height_" src="https://sms.cam.ac.uk/media/1119035/embed" frameborder="0" scrolling="no" allowfullscreen></iframe>

Choose size:

About this item

Available Formats

About this item

Description:	Rivoirard, V (Paris-Dauphine) Tuesday 22 March 2011, 16:00-17:00

Created:

2011-03-25 14:27

Collection:

Compressed Sensing LMS Series 2011

Publisher:

Isaac Newton Institute

Rivoirard, V

Language:

eng (English)

Credits:

Author:	Rivoirard, V
Director:	Steve Greenham


Abstract:	The Dantzig selector has been introduced by Emmanuel Candes and Terence Tao in an outstanding paper that deals with prediction and variable selection in the setting of the curse of dimensionality extensively considered in statistics recently. Using sparsity assumptions, variable selection performed by the Dantzig selector can improve estimation accuracy by effectively identifying the subset of important predictors, and then enhance model interpretability allowed by parsimonious representations. The goal of this talk is to present the main ideas of the paper by Candes and Tao and the remarkable results they obtained. We also wish to emphasize some of the extensions proposed in different settings and in particular for density estimation considered in the dictionary approach. Finally, connections between the Dantzig selector and the popular lasso procedure will be also highlighted.

Abstract:

The Dantzig selector has been introduced by Emmanuel Candes and Terence Tao in an outstanding paper that deals with prediction and variable selection in the setting of the curse of dimensionality extensively considered in statistics recently. Using sparsity assumptions, variable selection performed by the Dantzig selector can improve estimation accuracy by effectively identifying the subset of important predictors, and then enhance model interpretability allowed by parsimonious representations. The goal of this talk is to present the main ideas of the paper by Candes and Tao and the remarkable results they obtained. We also wish to emphasize some of the extensions proposed in different settings and in particular for density estimation considered in the dictionary approach. Finally, connections between the Dantzig selector and the popular lasso procedure will be also highlighted.

Available Formats

Format	Quality	Bitrate	Size
MPEG-4 Video	640x360	1.84 Mbits/sec	957.04 MB	View	Download
WebM	640x360	1.03 Mbits/sec	525.80 MB	View	Download
Flash Video	484x272	568.74 kbits/sec	287.36 MB	View	Download
iPod Video	480x270	506.25 kbits/sec	255.79 MB	View	Download
MP3	44100 Hz	125.01 kbits/sec	62.97 MB	Listen	Download
Auto *	(Allows browser to choose a format it supports)