Implement AME

Introduced in _Lin, Jinkun, Anqi Zhang, Mathias Lécuyer, Jinyang Li, Aurojit Panda, and Siddhartha Sen. “[Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments](https://proceedings.mlr.press/v162/lin22h.html).” In Proceedings of the 39th International Conference on Machine Learning, 13468–504. PMLR, 2022._

For the "exact" AME, a very similar sampling scheme to Owen sampling makes for a trivial implementation.

The issue references a specific ML paper on AME (Average Marginal Effect). Start by reading the linked paper to understand the algorithm. Look for existing Owen sampling implementations in the pyDVL codebase as a reference. The implementation likely belongs in a module related to data valuation or sampling. Check the repository structure for relevant directories and tests to understand the codebase's patterns.

由索引模型根据 Issue 内容生成。