A Simple and Efficient Tensor Calculus for Machine Learning

TL;DR

This paper introduces a new tensor calculus algorithm based on Einstein notation, offering a simpler, more efficient alternative to Ricci notation for derivatives in machine learning frameworks, with practical implementation.

Contribution

The paper develops an Einstein notation-based tensor calculus method that matches the efficiency of Ricci notation approaches, enabling integration into popular deep learning frameworks.

Findings

The new method achieves higher efficiency in tensor derivatives computation.

Implementation is available at www.MatrixCalculus.org.

The approach simplifies tensor calculus without sacrificing performance.

Abstract

Computing derivatives of tensor expressions, also known as tensor calculus, is a fundamental task in machine learning. A key concern is the efficiency of evaluating the expressions and their derivatives that hinges on the representation of these expressions. Recently, an algorithm for computing higher order derivatives of tensor expressions like Jacobians or Hessians has been introduced that is a few orders of magnitude faster than previous state-of-the-art approaches. Unfortunately, the approach is based on Ricci notation and hence cannot be incorporated into automatic differentiation frameworks from deep learning like TensorFlow, PyTorch, autograd, or JAX that use the simpler Einstein notation. This leaves two options, to either change the underlying tensor representation in these frameworks or to develop a new, provably correct algorithm based on Einstein notation. Obviously, the first option is impractical. Hence, we pursue the second option. Here, we show that using Ricci notation is not necessary for an efficient tensor calculus and develop an equally efficient method for the simpler Einstein notation. It turns out that turning to Einstein notation enables further improvements that lead to even better efficiency. The methods that are described in this paper have been implemented in the online tool www.MatrixCalculus.org for computing derivatives of matrix and tensor expressions. An extended abstract of this paper appeared as "A Simple and Efficient Tensor Calculus", AAAI 2020.