Keras Sig 用GPU加速路径签名计算，训练提速55%。
Keras Sig: Efficient Path Signature Computation on GPU in Keras 3
- 基于Keras 3重构签名计算，利用GPU并行性提升效率。
- 相比现有方法，签名计算速度提升5至10倍，训练时间减少55%。
- 兼容PyTorch/JAX/TensorFlow，适合需要高效签名的深度学习研究者。
本文提出Keras Sig，一个专为深度学习设计的高性能路径签名计算库，完全基于Keras 3构建。它无缝集成主流深度学习后端（如PyTorch、JAX、TensorFlow），受Kidger和Lyons（2021）启发，通过重构签名计算方式以充分利用GPU并行能力。该方法使训练时间减少55%，直接签名计算速度提升5至10倍，同时保持与现有方法相当的CPU性能。相较于依赖底层C++代码的实现，Keras Sig采用高层张量操作，显著降低版本与兼容性问题，在多种硬件配置下表现优异或相当。大量基准测试表明，该方法在输入序列长度增长时仍具高效扩展性，且在各类签名参数下保持竞争力，仅受限于大维度签名的内存瓶颈。
原文摘要 · Abstract (English)
In this paper we introduce Keras Sig a high-performance pythonic library designed to compute path signature for deep learning applications. Entirely built in Keras 3, \textit{Keras Sig} leverages the seamless integration with the mostly used deep learning backends such as PyTorch, JAX and TensorFlow. Inspired by Kidger and Lyons (2021),we proposed a novel approach reshaping signature calculations to leverage GPU parallelism. This adjustment allows us to reduce the training time by 55\% and 5 to 10-fold improvements in direct signature computation compared to existing methods, while maintaining similar CPU performance. Relying on high-level tensor operations instead of low-level C++ code, Keras Sig significantly reduces the versioning and compatibility issues commonly encountered in deep learning libraries, while delivering superior or comparable performance across various hardware configurations. We demonstrate through extensive benchmarking that our approach scales efficiently with the length of input sequences and maintains competitive performance across various signature parameters, though bounded by memory constraints for very large signature dimensions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。