MLCOMay 31, 2017

Bayesian $l_0$-regularized Least Squares

arXiv:1706.00098v223 citations
Originality Incremental advance
AI Analysis

This work addresses computational speed and scalability issues in Bayesian variable selection for statisticians and data scientists, representing an incremental improvement over existing methods.

The paper tackles the challenge of optimizing a non-convex objective function for Bayesian variable selection in high-dimensional predictors by linking Bayesian regularization to proximal updating, enabling the use of Single Best Replacement (SBR) to efficiently find spike-and-slab estimators, with simulation and real data showing improved computational efficiency.

Bayesian $l_0$-regularized least squares is a variable selection technique for high dimensional predictors. The challenge is optimizing a non-convex objective function via search over model space consisting of all possible predictor combinations. Spike-and-slab (a.k.a. Bernoulli-Gaussian) priors are the gold standard for Bayesian variable selection, with a caveat of computational speed and scalability. Single Best Replacement (SBR) provides a fast scalable alternative. We provide a link between Bayesian regularization and proximal updating, which provides an equivalence between finding a posterior mode and a posterior mean with a different regularization prior. This allows us to use SBR to find the spike-and-slab estimator. To illustrate our methodology, we provide simulation evidence and a real data example on the statistical properties and computational efficiency of SBR versus direct posterior sampling using spike-and-slab priors. Finally, we conclude with directions for future research.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes