Expert-guided Regularization via Distance Metric Learning
This addresses the problem of insufficiently leveraging expert knowledge in regularization for high-dimensional prediction, though it is incremental as it builds on existing regularization and metric learning methods.
The paper tackles the challenge of incorporating domain expert knowledge into high-dimensional prediction models by proposing Distance Metric Learning Regularization (DMLreg), which learns a distance metric from expert comparisons and uses it to regularize a linear model, resulting in improved model performance when the expert is knowledgeable.
High-dimensional prediction is a challenging problem setting for traditional statistical models. Although regularization improves model performance in high dimensions, it does not sufficiently leverage knowledge on feature importances held by domain experts. As an alternative to standard regularization techniques, we propose Distance Metric Learning Regularization (DMLreg), an approach for eliciting prior knowledge from domain experts and integrating that knowledge into a regularized linear model. First, we learn a Mahalanobis distance metric between observations from pairwise similarity comparisons provided by an expert. Then, we use the learned distance metric to place prior distributions on coefficients in a linear model. Through experimental results on a simulated high-dimensional prediction problem, we show that DMLreg leads to improvements in model performance when the domain expert is knowledgeable.