Robust, Efficient, and Local Machine Learning Primitives

Abstract

In this project, we develop, implement, and apply a suite of theoretically principled algorithmic and statistical primitives that are easy for the non-expert to use and that map cleanly to the intuition and understanding that domain experts have about their data and the processes generating their data. Most of our efforts focus on machine learning (ML) and data analysis (DA) primitives for analyzing data that are modeled by matrices or graphs, with an emphasis on primitives that (when combined appropriately) give complementary algorithmic and statistical advantage. Our main focus is on TA1, for which we develop a library of primitives, but we are also interested in TA2 questions having to do with how these primitives interact.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 2021
Accession Number
AD1125145

Entities

People

  • Michael W. Mahoney

Organizations

  • International Computer Science Institute

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Abstracts
  • Air Force
  • Air Force Research Laboratories
  • Algorithms
  • Artificial Intelligence
  • Artificial Intelligence Software
  • Automata Theory
  • Computer Science
  • Computers
  • Contracts
  • Data Analysis
  • Data Mining
  • Data Science
  • Dimensionality Reduction
  • Government Procurement
  • Governments
  • Information Exchange
  • Linear Algebra
  • Machine Learning
  • Military Research
  • Network Science
  • Neural Networks
  • Nonlinear Dynamics
  • Security
  • Statistical Mechanics
  • United States

Fields of Study

  • Computer science

Readers

  • Distributed Systems and Data Platform Development
  • Theoretical Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks