DerivKit: 稳定的数值导数连接Fisher预测与MCMC
DerivKit: stable numerical derivatives bridging Fisher forecasts and MCMC
AI总结：
DerivKit通过稳定数值导数连接Fisher预测与MCMC，提供高阶似然近似和非高斯展开方法。
摘要：
DerivKit是一个用于基于导数的统计推断的Python包。它实现了稳定的数值微分和导数组装工具，用于Fisher矩阵预测和更高阶似然近似在科学应用中，支持标量和向量值模型，包括黑箱或表格函数，其中自动微分不适用或不可用。这些导数用于构建基于导数近似似然（DALI）的Fisher预测、Fisher偏估计和非高斯似然展开。通过将基于导数的推断扩展到高斯近似之外，DerivKit在快速Fisher预测和计算上更密集的采样方法如马尔可夫链蒙特卡罗（MCMC）之间形成了实用的桥梁。
英文摘要：
DerivKit is a Python package for derivative-based statistical inference. It implements stable numerical differentiation and derivative assembly utilities for Fisher-matrix forecasting and higher-order likelihood approximations in scientific applications, supporting scalar- and vector-valued models including black-box or tabulated functions where automatic differentiation is impractical or unavailable. These derivatives are used to construct Fisher forecasts, Fisher bias estimates, and non-Gaussian likelihood expansions based on the Derivative Approximation for Likelihoods (DALI). By extending derivative-based inference beyond the Gaussian approximation, DerivKit forms a practical bridge between fast Fisher forecasts and more computationally intensive sampling-based methods such as Markov chain Monte Carlo (MCMC).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
