mlsanityData to 7 Oct 2026

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

arXiv 2001.00706 ↗First posted 3 Jan 2020cs.LG stat.MLcited by 45

Not on the map. Why?

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.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Jan 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 3; 2023: 10; 2024: 11; 2025: 3; 2026: 8.

45 papers.

Sort:

By area:

  1. 2021Neural SDEs as Infinite-Dimensional GANscited by 159
  2. 2021Efficient and Accurate Gradients for Neural SDEscited by 68
  3. 2021Neural Controlled Differential Equations for Online Prediction Taskscited by 46
  4. 2022Signature Methods in Machine Learningcited by 33
  5. 2021Framing RNN as a kernel method: A neural ODE approachcited by 23
  6. 2021Probabilistic Inference of Simulation Parameters via Parallel Differentiable Simulationcited by 17
  7. 2024Rough Transformers: Lightweight and Continuous Time Series Modelling through Signature Patchingcited by 16
  8. 2024Lecture notes on rough paths and applications to machine learningcited by 13
  9. 2021Signatured Deep Fictitious Play for Mean Field Games with Common Noisecited by 12
  10. 2021Logsig-RNN: a novel network for robust and efficient skeleton-based action recognitioncited by 10
  11. 2023Random Fourier Signature Featurescited by 9
  12. 2023SigFormer: Signature Transformers for Deep Hedgingcited by 7
33 more
  1. 2024Dynamical Survival Analysis with Controlled Latent Statescited by 7
  2. 2024Sparse Signature Coefficient Recovery via Kernelscited by 5
  3. 2025pySigLib -- Fast Signature-Based Computations on CPU and GPUcited by 5
  4. 2024Novelty Detection on Radio Astronomy Data using Signaturescited by 4
  5. 2021BayesSimIG: Scalable Parameter Inference for Adaptive Domain Randomization with IsaacGymcited by 3
  6. 2023Learning the Dynamics of Sparsely Observed Interacting Systemscited by 3
  7. 2024Explorative Imitation Learning: A Path Signature Approach for Continuous Environmentscited by 3
  8. 2022ImageSig: A signature transform for ultra-lightweight image recognitioncited by 2
  9. 2023A Neural RDE-based model for solving path-dependent PDEscited by 2
  10. 2023Sig-Networks Toolkit: Signature Networks for Longitudinal Language Modellingcited by 2
  11. 2025Hedging with memory: shallow and deep learning with signaturescited by 2
  12. 2021Path Signature Area-Based Causal Discovery in Coupled Time Seriescited by 1
  13. 2023Neural SDEs for Conditional Time Series Generation and the Signature-Wasserstein-1 metriccited by 1
  14. 2023Deep incremental learning models for financial temporal tabular datasets with distribution shiftscited by 1
  15. 2024Transportation Marketplace Rate Forecast Using Signature Transformcited by 1
  16. 2026Generating Financial Time Series by Matching Random Convolutional Featurescited by 1
  17. 2026TRACE: Trajectory-Routed Causal Memory for Delayed-Evidence Visuomotor Imitationcited by 1
  18. 2021From augmented microscopy to the topological transformer: a new approach in cell image analysis for Alzheimer's researchcited by 0
  19. 2022Signature and Log-signature for the Study of Empirical Distributions Generated with GANscited by 0
  20. 2023Feature Engineering Methods on Multivariate Time-Series Data for Financial Data Science Competitionscited by 0
  21. 2023Generating drawdown-realistic financial price paths using path signaturescited by 0
  22. 2023Gaussian processes based data augmentation and expected signature for time series classificationcited by 0
  23. 2024Path Signatures and Graph Neural Networks for Slow Earthquake Analysis: Better Together?cited by 0
  24. 2024Log-PDE Methods for Rough Signature Kernelscited by 0
  25. 2024Mean Field Correlated Imitation Learningcited by 0
  26. 2024Deep Signature: Characterization of Large-Scale Molecular Dynamicscited by 0
  27. 2025Novelty detection on path spacecited by 0
  28. 2026pathsig: A GPU-Accelerated Library for Truncated and Projected Path Signaturescited by 0
  29. 2026Online Goal Recognition using Path Signature and Dynamic Time Warpingcited by 0
  30. 2026Branched Signature Kernel Solvers for ODEs with rough Single-Trajectory signalscited by 0
  31. 2026Probabilistic Signature Inversion: Learning Conditional Distributions from Truncated Signaturescited by 0
  32. 2026Heavy-Tailed Flow Matching via Random Clockscited by 0
  33. 2026Time series generation with spectrally aligned latent flow matchingcited by 0