User Tools

Site Tools



This shows you the differences between two versions of the page.

Link to this comparison view

a_new_approach_to_robustness_and_flexibility_in_high-dimensions [2016/09/01 19:15] (current)
Line 1: Line 1:
 +Title: A New Approach to Robustness and Flexibility in High-dimensions
 +High-dimensional problems are those where the number of variables to estimate/​decide on vastly outnumber the number of observations. Several popular methods for the same impose structural models on the data (e.g. low-rank, sparse, Markov assumptions etc.). These methods however are both very fragile to gross/​adversarial corruptions,​ and overly restrictive in their modeling capability.
 +We propose the simultaneous use of more than structural model for high-dimensional problems. Our approach yields several new methods that are much more widely applicable, and significantly more robust, than existing ones - often with only slightly larger
 +computational complexity. We present new methods, and corresponding analytical results, for
 +(a) PCA in the presence of arbitrary outliers and corruptions
 +(b) Robust Collaborative filtering
 +(c) Multiple sparse regression/​compressed sensing with partially shared sparsity
 +(d) Graph clustering
 +Our methods are based on convex optimization.
 +Sujay Sanghavi is an Assistant Professor in ECE at UT Austin. He obtained his PhD from UIUC in 2006, and was a postdoctoral associate in LIDS, MIT until 2008. Sujay'​s research lies at the intersection of large-scale networks (communication and social), and statistical machine learning and inference. He got the NSF CAREER award in 2010.
a_new_approach_to_robustness_and_flexibility_in_high-dimensions.txt ยท Last modified: 2016/09/01 19:15 (external edit)