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

28 Sept 2020, 15:50 (modified: 10 Feb 2022, 11:42)ICLR 2021 PosterReaders: Everyone
Keywords: signature, logsignature, gpu, library, open source
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.
One-sentence Summary: Differentiable, GPU-capable implementations of the (log)signature transform via novel algorithms.
Supplementary Material: zip
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Code: [![github](/images/github_icon.svg) patrick-kidger/signatory](https://github.com/patrick-kidger/signatory)
13 Replies

Loading