Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPU
This provides a GPU-capable tool for machine learning applications, addressing a bottleneck in processing sequential data, though it is incremental as it builds on existing transform methods.
The authors developed Signatory, a library for differentiable computations of signature and logsignature transforms with CPU and GPU support, achieving substantial real-world speedups through novel algorithmic improvements.
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.