ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2204.01668
27
11

Scalable Spike-and-Slab

4 April 2022
N. Biswas
Lester W. Mackey
Xiao-Li Meng
    GP
ArXivPDFHTML
Abstract

Spike-and-slab priors are commonly used for Bayesian variable selection, due to their interpretability and favorable statistical properties. However, existing samplers for spike-and-slab posteriors incur prohibitive computational costs when the number of variables is large. In this article, we propose Scalable Spike-and-Slab (S3S^3S3), a scalable Gibbs sampling implementation for high-dimensional Bayesian regression with the continuous spike-and-slab prior of George and McCulloch (1993). For a dataset with nnn observations and ppp covariates, S3S^3S3 has order max⁡{n2pt,np}\max\{ n^2 p_t, np \}max{n2pt​,np} computational cost at iteration ttt where ptp_tpt​ never exceeds the number of covariates switching spike-and-slab states between iterations ttt and t−1t-1t−1 of the Markov chain. This improves upon the order n2pn^2 pn2p per-iteration cost of state-of-the-art implementations as, typically, ptp_tpt​ is substantially smaller than ppp. We apply S3S^3S3 on synthetic and real-world datasets, demonstrating orders of magnitude speed-ups over existing exact samplers and significant gains in inferential quality over approximate samplers with comparable cost.

View on arXiv
Comments on this paper