统一多种自动微分工具，让科研代码更易比较与开发。
A Common Interface for Automatic Differentiation
- 提供统一前端接口，连接十余种AD后端。
- 通过预处理机制复用计算，提升稀疏性等复杂功能效率。
- 适合需要灵活切换AD工具的科学机器学习研究者。
在包含大量自定义代码的科学机器学习任务中，选择合适的自动微分（AD）系统至关重要。我们的Julia包DifferentiationInterface.jl提供了一个通用前端，对接十余种AD后端，实现了便捷的对比与模块化开发。其内置的预处理机制通过摊销一次性计算，充分发挥各后端优势，是实现稀疏性处理等复杂功能的关键，且无需增加用户负担。
原文摘要 · Abstract (English)
For scientific machine learning tasks with a lot of custom code, picking the right Automatic Differentiation (AD) system matters. Our Julia package DifferentiationInterface$.$jl provides a common frontend to a dozen AD backends, unlocking easy comparison and modular development. In particular, its built-in preparation mechanism leverages the strengths of each backend by amortizing one-time computations. This is key to enabling sophisticated features like sparsity handling without putting additional burdens on the user.
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。