en-es
en
0.25
0.5
0.75
1.25
1.5
1.75
2
Algorithms and Hardness for Robust Subspace Recovery
Published on Aug 09, 20133835 Views
We consider a fundamental problem in unsupervised learning called subspace recovery: given a collection of m points in Rn, if many but not necessarily all of these points are contained in a d-dimensio
Related categories
Chapter list
Algorithms and Hardness for Robust Subspace Recovery00:00
Robust Subspace Recovery - 100:11
Robust Subspace Recovery - 201:14
Robust Subspace Recovery - 301:28
Example - 101:49
Example - 202:28
Robust Stats Terminology03:19
In this talk04:39
Lots of related work07:02
Overview09:08
Simple Randomized Algorithm - 109:33
Simple Randomized Algorithm - 210:48
Hardness13:45
Small set expansion14:15
Reduction from Gap-SSE16:22
Completeness / Soundness17:19
Summary18:27
Where’s the challenge?19:13
Open Problems20:10
Thank you20:55