Learning Data Representations via Nonconvex Optimization

Abstract

In this project we developed a unified understanding of how to design and analyze efficient nonconvex optimization algorithms aimed at learning interpretable representations from data. These data representations can in turn enable automatic knowledge extraction from observed low-level sensory data enhancing a variety of applications. Our main results during the second year can be summarized in three categories: (1) understanding the optimization landscape of data representation tasks such as matrix factorization and shallow neural network training, (2) developing principled approaches to utilizing prior knowledge in data representation tasks and characterizing the reduction in the size of the training data that results from such usage of prior knowledge, and (3) developing algorithmic variations that can be implemented on often unreliable modern cloud infrastructure.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 17, 2021
Accession Number
AD1146054

Entities

People

  • Mahdi Soltanolkotabi

Organizations

  • University of Southern California

Tags

Communities of Interest

  • Energy and Power Technologies
  • Engineered Resilient Systems

DTIC Thesaurus Topics

  • Accuracy
  • Acquisition
  • Air Force Research Laboratories
  • Algorithms
  • Artificial Intelligence
  • Artificial Intelligence Software
  • Compressed Sensing
  • Computations
  • Convolutional Neural Networks
  • Data Analysis
  • Data Mining
  • Data Sets
  • Information Science
  • Information Theory
  • Machine Learning
  • Neural Networks
  • Scientific Research
  • Statistical Analysis
  • Statistics
  • Training

Fields of Study

  • Computer science

Readers

  • Distributed Systems and Data Platform Development
  • Operations Research

Technology Areas

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