The Kernel Interaction Trick: Fast Bayesian Discovery of Pairwise Interactions in High Dimensions
[edit]
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:141150, 2019.
Abstract
Discovering interaction effects on a response of interest is a fundamental problem faced in biology, medicine, economics, and many other scientific disciplines. In theory, Bayesian methods for discovering pairwise interactions enjoy many benefits such as coherent uncertainty quantification, the ability to incorporate background knowledge, and desirable shrinkage properties. In practice, however, Bayesian methods are often computationally intractable for even moderate dimensional problems. Our key insight is that many hierarchical models of practical interest admit a Gaussian process representation such that rather than maintaining a posterior over all O(p^2) interactions, we need only maintain a vector of O(p) kernel hyperparameters. This implicit representation allows us to run Markov chain Monte Carlo (MCMC) over model hyperparameters in time and memory linear in p per iteration. We focus on sparsityinducing models and show on datasets with a variety of covariate behaviors that our method: (1) reduces runtime by orders of magnitude over naive applications of MCMC, (2) provides lower Type I and Type II error relative to stateoftheart LASSObased approaches, and (3) offers improved computational scaling in high dimensions relative to existing Bayesian and LASSObased approaches.
Related Material


