MSNANAMar 2, 2020

Tensor Train decomposition on TensorFlow (T3F)

OpenAI
arXiv:1801.0192881 citationsh-index: 52
AI Analysis

For researchers and practitioners using Tensor Train decomposition in machine learning, this library provides a practical tool with GPU support and Riemannian optimization, though it is an incremental contribution.

The authors present T3F, a TensorFlow-based library for Tensor Train decomposition that supports GPU execution, batch processing, automatic differentiation, and Riemannian optimization. The library aims to simplify implementation of machine learning papers using Tensor Train decomposition.

Tensor Train decomposition is used across many branches of machine learning. We present T3F -- a library for Tensor Train decomposition based on TensorFlow. T3F supports GPU execution, batch processing, automatic differentiation, and versatile functionality for the Riemannian optimization framework, which takes into account the underlying manifold structure to construct efficient optimization methods. The library makes it easier to implement machine learning papers that rely on the Tensor Train decomposition. T3F includes documentation, examples and 94% test coverage.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes