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

arXiv: https://arxiv.org/abs/2001.00706 · HTML: https://mlsanity.com/paper/2001.00706/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jan 2020.

## Built on by (most cited first, 30 of 46)

- [Neural SDEs as Infinite-Dimensional GANs](https://mlsanity.com/paper/2102.03657/) (2021)
- [Efficient and Accurate Gradients for Neural SDEs](https://mlsanity.com/paper/2105.13493/) (2021)
- [Neural Controlled Differential Equations for Online Prediction Tasks](https://mlsanity.com/paper/2106.11028/) (2021)
- [Signature Methods in Machine Learning](https://mlsanity.com/paper/2206.14674/) (2022)
- [Framing RNN as a kernel method: A neural ODE approach](https://mlsanity.com/paper/2106.01202/) (2021)
- [Probabilistic Inference of Simulation Parameters via Parallel Differentiable Simulation](https://mlsanity.com/paper/2109.08815/) (2021)
- [Rough Transformers: Lightweight and Continuous Time Series Modelling through Signature Patching](https://mlsanity.com/paper/2405.20799/) (2024)
- [Lecture notes on rough paths and applications to machine learning](https://mlsanity.com/paper/2404.06583/) (2024)
- [Signatured Deep Fictitious Play for Mean Field Games with Common Noise](https://mlsanity.com/paper/2106.03272/) (2021)
- [Logsig-RNN: a novel network for robust and efficient skeleton-based action recognition](https://mlsanity.com/paper/2110.13008/) (2021)
- [Random Fourier Signature Features](https://mlsanity.com/paper/2311.12214/) (2023)
- [SigFormer: Signature Transformers for Deep Hedging](https://mlsanity.com/paper/2310.13369/) (2023)
- [Dynamical Survival Analysis with Controlled Latent States](https://mlsanity.com/paper/2401.17077/) (2024)
- [Sparse Signature Coefficient Recovery via Kernels](https://mlsanity.com/paper/2412.08579/) (2024)
- [pySigLib -- Fast Signature-Based Computations on CPU and GPU](https://mlsanity.com/paper/2509.10613/) (2025)
- [Novelty Detection on Radio Astronomy Data using Signatures](https://mlsanity.com/paper/2402.14892/) (2024)
- [BayesSimIG: Scalable Parameter Inference for Adaptive Domain Randomization with IsaacGym](https://mlsanity.com/paper/2107.04527/) (2021)
- [Learning the Dynamics of Sparsely Observed Interacting Systems](https://mlsanity.com/paper/2301.11647/) (2023)
- [Explorative Imitation Learning: A Path Signature Approach for Continuous Environments](https://mlsanity.com/paper/2407.04856/) (2024)
- [Hedging with memory: shallow and deep learning with signatures](https://mlsanity.com/paper/2508.02759/) (2025)
- [ImageSig: A signature transform for ultra-lightweight image recognition](https://mlsanity.com/paper/2205.06929/) (2022)
- [A Neural RDE-based model for solving path-dependent PDEs](https://mlsanity.com/paper/2306.01123/) (2023)
- [Sig-Networks Toolkit: Signature Networks for Longitudinal Language Modelling](https://mlsanity.com/paper/2312.03523/) (2023)
- [Path Signature Area-Based Causal Discovery in Coupled Time Series](https://mlsanity.com/paper/2110.12288/) (2021)
- [Neural SDEs for Conditional Time Series Generation and the Signature-Wasserstein-1 metric](https://mlsanity.com/paper/2301.01315/) (2023)
- [Deep incremental learning models for financial temporal tabular datasets with distribution shifts](https://mlsanity.com/paper/2303.07925/) (2023)
- [Transportation Marketplace Rate Forecast Using Signature Transform](https://mlsanity.com/paper/2401.04857/) (2024)
- [Generating Financial Time Series by Matching Random Convolutional Features](https://mlsanity.com/paper/2606.05138/) (2026)
- [TRACE: Trajectory-Routed Causal Memory for Delayed-Evidence Visuomotor Imitation](https://mlsanity.com/paper/2606.14551/) (2026)
- [From augmented microscopy to the topological transformer: a new approach in cell image analysis for Alzheimer's research](https://mlsanity.com/paper/2108.01625/) (2021)

## Abstract (arXiv)

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 textttpip. Source code, documentation, examples, benchmarks and tests may be found at texttturlhttps://github.com/patrick-kidger/signatory. The license is Apache-2.0.