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

Abstract

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.

arXiv commentPublished at ICLR 2021

References in corpus (13)

• ANODE: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs
• Rough paths, Signatures and the modelling of functions on streams
• Learning from the past, predicting the statistics for the future, learning an evolving system
• Deep Signature Transforms
• Stochastic Normalizing Flows
• Learning stochastic differential equations using RNN with log signature features
• The iisignature library: efficient calculation of iterated-integral signatures and log signatures
• Application of the Signature Method to Pattern Recognition in the CEQUEL Clinical Trial
• Bayesian Learning from Sequential Data using Gaussian Processes with Signature Covariances
• Embedding and learning with signatures
• A Generalised Signature Method for Multivariate Time Series Feature Extraction
• Generalised Interpretable Shapelets for Irregular Time Series
• Path Imputation Strategies for Signature Models of Irregular Time Series

Cited by in corpus (18)

• Neural Controlled Differential Equations for Irregular Time Series
• Deep Signature Transforms
• Neural Rough Differential Equations for Long Time Series
• Logsig-RNN: a novel network for robust and efficient skeleton-based action recognition
• A Generalised Signature Method for Multivariate Time Series Feature Extraction
• Neural SDEs as Infinite-Dimensional GANs
• Framing RNN as a kernel method: A neural ODE approach
• SigFormer: Signature Transformers for Deep Hedging
• Generalised Interpretable Shapelets for Irregular Time Series
• Distribution Regression for Sequential Data
• Signatured Deep Fictitious Play for Mean Field Games with Common Noise
• Seq2Tens: An Efficient Representation of Sequences by Low-Rank Tensor Projections
• Path Signatures on Lie Groups
• Path Imputation Strategies for Signature Models of Irregular Time Series
• Learning the Dynamics of Sparsely Observed Interacting Systems
• Robust Hedging GANs
• Probabilistic Inference of Simulation Parameters via Parallel Differentiable Simulation
• From augmented microscopy to the topological transformer: a new approach in cell image analysis for Alzheimer's research