Stochastic Online Learning in Dynamic Networks under Unknown Models

Abstract

This research aims to develop fundamental theories and practical algorithms for distributed, robust, and real-time learning in dynamic tactical networks. The overall objective is to significantly move the frontiers of knowledge in stochastic learning in the classic multi-armed bandit by systematically relaxing traditionally adopted restrictive assumptions.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 02, 2016
Accession Number
AD1017108

Entities

People

  • Qing Zhao

Organizations

  • University of California, Davis

Tags

Communities of Interest

  • Sensors

DTIC Thesaurus Topics

  • Abstracts
  • Acoustics
  • Ad Hoc Networks
  • Algorithms
  • Communication Networks
  • Communication Systems
  • Computers
  • Department Of Defense
  • Dimensionality Reduction
  • Distance Learning
  • Engineering
  • Information Exchange
  • Information Operations
  • Information Processing
  • Information Theory
  • Learning
  • Mathematics
  • Mesh Networks
  • Military Research
  • Network Topology
  • Networks
  • Optimization
  • Probability
  • Random Variables
  • Signal Processing
  • Spine
  • Stochastic Processes
  • Tactical Networks
  • Workshops

Fields of Study

  • Computer science

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.