High Dimensional Learning

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.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 27, 2013
Accession Number
ADA604947

Entities

People

  • Anima Anandkumar

Organizations

  • University of California, Irvine

Tags

Communities of Interest

  • Autonomy
  • Biomedical

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence Software
  • Bayesian Networks
  • Computational Science
  • Computer Vision
  • Graphics Processing Unit
  • Information Processing
  • Information Theory
  • Machine Learning
  • Markov Models
  • Probabilistic Models
  • Probability
  • Probability Distributions
  • Random Variables
  • Signal Processing
  • Social Networks
  • Statistics

Fields of Study

  • Computer science

Readers

  • Artificial Intelligence
  • Computational Fluid Dynamics (CFD)
  • Statistical inference.