Multivariate Heavy Tail Phenomena: Modeling and Diagnostics

Abstract

This project develops reliable diagnostic, inferential and model validation tools for heavy tailed multivariate data; generates new classes of multivariate heavy tailed models that highlight the implications of dependence and tail weight; and applies these statistical and mathematical developments to the key application areas of network design and control, social network analysis, and cloud computing. Our application interests also include network security,anomaly detection, mobile application scheduling and risk analysis. To understand and exploit multivariate heavy tail phenomena in relevant application areas, our project contributes statistical, mathematical and software tools that provide: (a) Flexible and practical representations of multidimensional heavy tail distributions that permit reliable statistical analysis and inference; allow model discovery, selection and confirmation; quantify dependence; and overcome the curse of dimensionality. (b) Heavy tailed mathematical models that can be calibrated; which clearly exhibit the influence of dependence and tail weight; and which are appropriate to the applied context. (c) Exploitation of the new tools of multivariate heavy tail analysis to study social networks; mobile networks; network design and control; application scheduling in mobile devices and cloud computing; and robust network search.

Document Details

Document Type
DoD Grant Award
Publication Date
Jun 25, 2021
Source ID
W911NF1210385

Entities

People

  • Sidney Resnick

Organizations

  • Army Contracting Command
  • Cornell University
  • United States Army

Tags

Fields of Study

  • Computer science

Readers

  • Aerospace Engineering
  • Neural Network Machine Learning.
  • Regression Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • Cyber
  • Cyber - Quantum