{"ID":2871911,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.10613","arxiv_id":"2509.10613","title":"pySigLib -- Fast Signature-Based Computations on CPU and GPU","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2509.10613","url_pdf":"https://arxiv.org/pdf/2509.10613v1","authors":"[\"Daniil Shmelev\",\"Cristopher Salvi\"]","published":"2025-09-12T18:00:14Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.MS\",\"stat.ML\"]","methods":"[]","has_code":false}