A User's Guide to $\texttt{KSig}$: GPU-Accelerated Computation of the Signature Kernel

TL;DR

This paper introduces $ exttt{KSig}$, a GPU-accelerated Python package for efficient computation of signature kernels in sequential data, featuring a new tensor sketch algorithm for improved performance.

Contribution

The paper presents $ exttt{KSig}$, a scalable, GPU-compatible Python package with a novel tensor sketch algorithm for signature kernel computation.

Findings

Tensor sketch algorithm outperforms existing methods

Package achieves scalable GPU-accelerated computation

Supports downstream learning tasks with signature kernels

Abstract

The signature kernel is a positive definite kernel for sequential and temporal data that has become increasingly popular in machine learning applications due to powerful theoretical guarantees, strong empirical performance, and recently introduced various scalable variations. In this chapter, we give a short introduction to $\texttt{KSig}$, a $\texttt{Scikit-Learn}$ compatible Python package that implements various GPU-accelerated algorithms for computing signature kernels, and performing downstream learning tasks. We also introduce a new algorithm based on tensor sketches which gives strong performance compared to existing algorithms. The package is available at https://github.com/tgcsaba/ksig.