High Dimensional Learning

reportActive / Technical Report | Accession Number: ADA604947 | Open PDF

Abstract:

The problem of high dimensional learning is considered. Efficient methods are developed for learning latent variable models and graphical models in high dimensions. Theoretical guarantees are established for the developed methods. The methods are applied to various domains including social networks and computational biology.

Author(s):
Anandkumar, Animashree
Author Organization(s):
CALIFORNIA UNIV IRVINE
Descriptive Note:
Final rept. 1 Oct 2012-30 Jun 2013
Supplementary Note:
The original document contains color images. DOI: 10.21236/ADA604947
Pagination:
0014

Security Markings

DOCUMENT & CONTEXTUAL SUMMARY

Distribution:
Approved For Public Release
Distribution Statement:
Approved For Public Release; Distribution Is Unlimited.

RECORD

Collection: TR
Identifying Numbers
Report Number(s):
ARO-62594-NS-II.8
Contract/Grant Number(s):
W911NF-12-1-0404
Monitor Series:
62594-NS-II.8, ARO
 Subject Terms
Joint Capability Areas:
JCA_6_Net Centric; JCA_6.1_Information Transport; JCA_5_Command and Control; JCA_5.3_Planning; JCA_1.2_Force Preparation; JCA_1_Force Support; JCA_4.6_Engineering; JCA_8_Building Partnerships
Modernization Areas:
Autonomy
Communities of Interest:
Biomedical
Descriptor(s):
*LEARNING MACHINES, DATA PROCESSING
Field(s)/Group(s):
Cybernetics
Keyword(s):
GRAPH ESTIMATION, GRAPHICAL MODELS, HIGH DIMENSIONAL LEARNING, LATENT VARIABLE MODELS, SPECTRAL METHODS, PE611102
Report Date:
2013 Aug 27
Creation Date:
2014 Aug 20