NIPS 2010 - NIPS 2010 Workshop on Robust Statistical Learning

Website | Edit Freely

Category NIPS 2010

Deadline: November 09, 2010 | Date: December 11, 2010

Venue/Country: Whistler, Canada

Updated: 2010-10-10 08:27:50 (GMT+9)

Call For Papers - CFP

Workshop at the 24th Annual Conference on Neural Information

Processing Systems (NIPS 2010)

http://www.cs.utexas.edu/~sai/robustml

Submission Deadline: Nov 09, 2010

There has been a resurgence of robust learning methods (broadly

understood) in recent years, largely from different communities that

rarely interact: (classical) robust statistics, adversarial machine

learning, robust optimization, and multi-structured or dirty model

learning. This workshop aims to bring together researchers from these

different communities, and identify potential common intuitions

underlying such robust learning methods. We are interested in

understanding where techniques from one field might be applicable, and

what their limitations are. As one very important example, we will

consider the high dimensional regime, where it is not clear how to

extend many of the techniques successful in the classical robust

statistics setup. There has been a massive amount of recent interest

and work in modeling such high-dimensional data, and the natural

extension of such results would be to make them more robust. Indeed,

with increasingly high-dimensional and "dirty" real world data that do

not conform to clean modeling assumptions, this is a vital necessity.

We would like to encourage high quality submissions of short papers

relevant to the workshop. Accepted papers will be presented as

spotlight talks and posters. Of particular interest are papers in the

following topics:

(a) Dirty Models: these invoke a combination of structural assumptions

such as sparsity, low-rank etc. to develop a robust estimation method.

(b) Robust Optimization: these use techniques from convexity and

duality, to construct solutions that are immunized from some bounded

level of uncertainty, typically expressed as bounded (but otherwise

arbitrary, i.e., adversarial) perturbations of the decision

parameters.

(c) Classical Robust Statistics; Adversarial Learning: these are

robust to misspecified modeling assumptions in general, and do not

model the outliers specifically.

Submission deadline: Nov 09, 2010

Length & Format: max. 6 pages NIPS 2010 format

Time & Location: December 10 2010, Whistler, Canada

Submission instructions: Via email to robustml.nipsgmail.com

Organizers: Pradeep Ravikumar, Constantine Caramanis, Sujay Sanghavi

(UT Austin)