mlsanityData to 14 Oct 2026

pySigLib -- Fast Signature-Based Computations on CPU and GPU

arXiv 2509.10613 ↗First posted 12 Sep 2025cs.LG cs.MS stat.MLcited by 6

Not on the map. Why?

Abstract (arXiv)

Signature-based methods have recently gained significant traction in machine learning for sequential data. In particular, signature kernels have emerged as powerful discriminators and training losses for generative models on time-series, notably in quantitative finance. However, existing implementations do not scale to the dataset sizes and sequence lengths encountered in practice. We present pySigLib, a high-performance Python library offering optimised implementations of signatures and signature kernels on CPU and GPU, fully compatible with PyTorch's automatic differentiation. Beyond an efficient software stack for large-scale signature-based computation, we introduce a novel differentiation scheme for signature kernels that delivers accurate gradients at a fraction of the runtime of existing libraries.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 24 of its 47 references that are in the map. First posted on arXiv 12 Sep 2025.

Builds on

24 of 47 references.

References · 24

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2020Neural Rough Differential Equations for Long Time Seriescited by 143
  3. 2016A Primer on the Signature Method in Machine Learningcited by 104
  4. 2016Kernels for sequentially ordered datacited by 84
  5. 2019Deep Signature Transformscited by 75
  6. 2020The Signature Kernel is the solution of a Goursat PDEcited by 58
  7. 2021Neural Stochastic PDEs: Resolution-Invariant Learning of Continuous Spatiotemporal Dynamicscited by 47
  8. 2020Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPUcited by 46
  9. 2018The iisignature library: efficient calculation of iterated-integral signatures and log signaturescited by 40
  10. 2023Non-adversarial training of Neural SDEs with signature kernel scorescited by 37
  11. 2020A Data-driven Market Simulator for Small Data Environmentscited by 35
  12. 2020Distribution Regression for Sequential Datacited by 31
12 more
  1. 2021Higher Order Kernel Mean Embeddings to Capture Filtrations of Stochastic Processescited by 27
  2. 2023Neural signature kernels as infinite-width-depth-limits of controlled ResNetscited by 25
  3. 2021SigGPDE: Scaling Sparse Gaussian Processes on Sequential Datacited by 22
  4. 2024Signature Kernel Conditional Independence Tests in Causal Discovery for Stochastic Processescited by 18
  5. 2025Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Modelscited by 18
  6. 2021SK-Tree: a systematic malware detection algorithm on streaming trees via the signature kernelcited by 16
  7. 2023A Neural RDE approach for continuous-time non-Markovian stochastic control problemscited by 14
  8. 2023New directions in the applications of rough path theorycited by 12
  9. 2023Signature Methods in Stochastic Portfolio Theorycited by 11
  10. 2024Exact Gradients for Stochastic Spiking Neural Networks Driven by Rough Signalscited by 9
  11. 2024Sparse Signature Coefficient Recovery via Kernelscited by 6
  12. 2025ParallelFlow: Parallelizing Linear Transformers via Flow Discretizationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2025Explicit and Effectively Symmetric Schemes for Neural SDEs on Lie Groupscited by 1
  2. 2025Novelty detection on path spacecited by 0
  3. 2026Branched Signature Kernel Solvers for ODEs with rough Single-Trajectory signalscited by 0
  4. 2026Learning Manifold and Ito Dynamics with Branched Neural Rough Differential Equationscited by 0
  5. 2026Improving Function Space Flow Matching with Kernel Optimal Transportcited by 0
  6. 2026HyperNSDE: Personalized Neural SDEs for Joint Static-Longitudinal Clinical Data Generationcited by 0