Implement Gradient Shapley

Algorithm 2 of _Ghorbani, Amirata, and James Zou. [Data Shapley: Equitable Valuation of Data for Machine Learning](http://proceedings.mlr.press/v97/ghorbani19c.html). In International Conference on Machine Learning, 2242–51. PMLR, 2019._

Note that this is not a true approximation to Shapley value, since it reuses the computation of the utility on a subset to compute it on another. In particular, the marginal utility is the difference in performance after one SGD step, which is not equivalent to a full retraining. As such this breaks several assumptions, e.g. that the sequence in which one adds samples to a coalition does not affect its utility, or that the utility computations are independent.

The issue references Algorithm 2 from the linked paper. Start by reading the paper to understand the Gradient Shapley method and its assumptions. Look for existing implementations of data valuation algorithms in the pyDVL codebase, likely in a module like pydvl.value. The task involves implementing the algorithm, which requires understanding of Shapley values, SGD, and utility computations. 'Done' means the new algorithm is integrated and tested.

Escrito por el modelo de indexación a partir del texto del issue.