Harnessing Parameterization For Fast And Reliable Nonconvex Optimization

Abstract

This project focused on developing novel understanding of large-scale, non-convex optimization problems by establishing robust notions of how the choice of parameterization affects the geometric and computational character of the optimization process. This understanding was used to create a methodological link between machine learning and optimal control, enabling a car to be successfully taught to drive around an unspecified track using vision-based control. Reparameterization also provided benefits for optimization of recurrent neural networks. Insights were gained into the construction of well-performing stable recurrent models for future used in machine learning.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 04, 2019
Accession Number
AD1090441

Entities

People

  • Asuman Özdağlar
  • Benjamin Recht
  • Pablo Parrilo

Organizations

  • University of California, Berkeley

Tags

Communities of Interest

  • Autonomy
  • Space

DTIC Thesaurus Topics

  • Air Force
  • Air Force Research Laboratories
  • Algorithms
  • Artificial Intelligence Software
  • Autonomous Systems
  • California
  • Closed Loop Systems
  • Computer Science
  • Control Systems
  • Information Systems
  • Learning
  • Machine Learning
  • Neural Networks
  • Optimization
  • Recurrent Neural Networks
  • United States
  • Unmanned Vehicles

Readers

  • Neural Network Machine Learning.
  • Operations Research
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks