Valid Inference for Machine Learning Model Parameters

Author name not available (Why is that?)

Publication date: 21 February 2023

Abstract: The parameters of a machine learning model are typically learned by minimizing a loss function on a set of training data. However, this can come with the risk of overtraining; in order for the model to generalize well, it is of great importance that we are able to find the optimal parameter for the model on the entire population -- not only on the given training sample. In this paper, we construct valid confidence sets for this optimal parameter of a machine learning model, which can be generated using only the training data without any knowledge of the population. We then show that studying the distribution of this confidence set allows us to assign a notion of confidence to arbitrary regions of the parameter space, and we demonstrate that this distribution can be well-approximated using bootstrapping techniques.

Has companion code repository: https://github.com/neil-dey/valid-inference-ml-estimators

This page was built for publication: Valid Inference for Machine Learning Model Parameters

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6427189)