Smoothed Analysis in Unsupervised Learning via Decoupling

Aidao Chen
Aidao Chen
Aidan Perreault
Aidan Perreault

2019 IEEE 60TH ANNUAL SYMPOSIUM ON FOUNDATIONS OF COMPUTER SCIENCE (FOCS 2019), pp. 582.0-610, 2019.

Cited by: 3|Bibtex|Views10|Links
EI
Keywords:
smoothed analysisunsupervised learningtensor decompositionsubspace recoveryhidden markov modelMore(2+)

Abstract:

Smoothed analysis is a powerful paradigm in overcoming worst-case intractability in unsupervised learning and high-dimensional data analysis. While polynomial time smoothed analysis guarantees have been obtained for worst-case intractable problems like tensor decompositions and learning mixtures of Gaussians, such guarantees have been har...More

Code:

Data:

Your rating :
0

 

Tags
Comments