Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Scalable Spike-and-Slab
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use S^3 precomputation and state updates instead of recomputing the sampler matrices from scratch | Bayesian spike-and-slab regression · Synthetic binary classification, n=4000, p=40000, s=400 | runtime per iteration: 335000ms -> 1100ms | Helped |
| Use S^3 instead of the SOTA sampler | Bayesian logistic regression · Synthetic binary classification, n=4000, p=40000, s=400 | runtime per iteration: 335000ms -> 21500ms | Helped |
| Use S^3 instead of Skinny Gibbs | Bayesian logistic regression · Synthetic binary classification, n=4000, p=40000, s=400 | runtime per iteration: 55600ms -> 21500ms | Helped |
| Use exact S^3 sampling instead of Skinny Gibbs | Bayesian variable selection · Synthetic binary classification, higher dimensions | true positive rate | Helped |
| Use exact S^3 sampling instead of Skinny Gibbs | Bayesian variable selection · Synthetic binary classification, higher dimensions | false discovery rate | Helped |
| Use S^3 instead of SOTA | Bayesian logistic regression · Gordon microarray | runtime per iteration: 20 times faster | Helped |
| Use S^3 instead of SOTA | Bayesian probit regression · Gordon microarray | runtime per iteration: 6 times faster | Helped |
| Use S^3 logistic instead of Skinny Gibbs | Bayesian logistic regression · Gordon microarray | runtime per iteration: 100 times faster | Helped |
| Use S^3 instead of the SOTA sampler | Bayesian linear regression · Maize GWAS | runtime per iteration: 31300ms -> 650ms | Helped |
Closest papers by meaning
- Select-and-Sample for Spike-and-Slab Sparse Coding (NeurIPS 2016 · similarity 0.89)
- Bayesian Joint Spike-and-Slab Graphical Lasso (ICML 2019 · similarity 0.89)
- Spike and slab variational Bayes for high dimensional logistic regression (NeurIPS 2020 · similarity 0.87)
- Scalable Nonparametric Sampling from Multimodal Posteriors with the Posterior Bootstrap (ICML 2019 · similarity 0.86)
- Scalable Bayesian Learning with posteriors (ICLR 2025 · similarity 0.85)
- Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion Models (ICML 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.