The iisignature library: efficient calculation of iterated-integral signatures and log signatures

Abstract

Iterated-integral signatures and log signatures are vectors calculated from a path that characterise its shape. They come from the theory of differential equations driven by rough paths, and also have applications in statistics and machine learning. We present algorithms for efficiently calculating these signatures, and benchmark their performance. We release the methods as a Python package.

arXiv comment18 pages

References in corpus (3)

• Algebraic Relations Between Harmonic Sums and Associated Quantities
• An efficient algorithm for computing the Baker-Campbell-Hausdorff series and some of its applications
• Rotation invariants of two dimensional curves based on iterated integrals

Cited by in corpus (12)

• Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPU
• Deep Signature Transforms
• Learning stochastic differential equations using RNN with log signature features
• Neural Rough Differential Equations for Long Time Series
• Logsig-RNN: a novel network for robust and efficient skeleton-based action recognition
• Embedding and learning with signatures
• A Generalised Signature Method for Multivariate Time Series Feature Extraction
• Distribution Regression for Sequential Data
• Seq2Tens: An Efficient Representation of Sequences by Low-Rank Tensor Projections
• Signature features with the visibility transformation
• SigGPDE: Scaling Sparse Gaussian Processes on Sequential Data
• Path Imputation Strategies for Signature Models of Irregular Time Series