Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPU

TL;DR

Signatory is a pioneering library that enables differentiable computation of signature and logsignature transforms on CPU and GPU, offering significant speedups and new features for machine learning applications.

Contribution

It introduces the first GPU-capable library for these transforms, with novel algorithms and efficient precomputation strategies, enhancing performance and usability in ML workflows.

Findings

First GPU-capable library for signature transforms

Achieves substantial speedups on CPU and GPU

Includes new algorithms and precomputation methods

Abstract

Signatory is a library for calculating and performing functionality related to the signature and logsignature transforms. The focus is on machine learning, and as such includes features such as CPU parallelism, GPU support, and backpropagation. To our knowledge it is the first GPU-capable library for these operations. Signatory implements new features not available in previous libraries, such as efficient precomputation strategies. Furthermore, several novel algorithmic improvements are introduced, producing substantial real-world speedups even on the CPU without parallelism. The library operates as a Python wrapper around C++, and is compatible with the PyTorch ecosystem. It may be installed directly via \texttt{pip}. Source code, documentation, examples, benchmarks and tests may be found at \texttt{\url{https://github.com/patrick-kidger/signatory}}. The license is Apache-2.0.