Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments

1 code implementation • 20 Jun 2022 • JinKun Lin, Anqi Zhang, Mathias Lecuyer, Jinyang Li, Aurojit Panda, Siddhartha Sen

Our algorithm estimates the AME, a quantity that measures the expected (average) marginal effect of adding a data point to a subset of the training data, sampled from a given distribution.

Causal Inference