Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Distributed Bayesian Varying Coefficient Modeling Using a Gaussian Process Prior
Rajarshi Guhaniyogi, Cheng Li, Terrance D. Savitsky, Sanvesh Srivastava
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| increase subset size from m=500 to m=1000 (ablation) | AMC · Simulated VCM n=3000 (k=10) | MSE: 0.56 -> 0.48 | Improved |
| increase number of subsets k from 10 to 20 at fixed m=1000 (ablation) | AMC · Simulated VCM n=3000 | MSE: 0.48 -> 0.48 | No clear effect |
| use AMC combination instead of CMC combination | subset posteriors · Simulated VCM n=3000 (m=1000, k=20) | 95% CI coverage: 0.39 -> 0.97 | Improved |
| use AMC combination instead of CMC combination | subset posteriors · Simulated VCM n=9000 (m=1000, k=60) | 95% CI coverage: 0.24 -> 0.98 | Improved |
| use distributed AMC instead of full-data posterior | Bayesian VCM · Simulated VCM n=3000 (m=1000, k=20) | computational efficiency: 2.10 -> 8.37 | Improved |
| use full-data posterior instead of AMC | Bayesian VCM · Simulated VCM n=3000 (m=1000, k=20) | MSE: 0.48 -> 0.40 | Improved |
| model bivariate response jointly instead of marginal spSVC | Bayesian VCM · Simulated VCM n=3000 | MSE: 7.24 -> 0.48 | Improved |
| use AMC instead of marginal spSVC | VCM inference · Simulated VCM n=3000 (m=1000, k=20) | 95% CI coverage: 0.27 -> 0.97 | Improved |
| increase sample size from n=3000 to n=9000 with AMC | AMC · Simulated VCM (m=1000) | MSE: 0.48 -> 0.38 | Improved |
| combine via AMC rather than PIE | subset posteriors · Simulated VCM n=3000 (m=1000, k=10) | 95% CI length: 3.02 -> 2.88 | Improved |
Closest papers by meaning
- Bayesian Data Sketching for Varying Coefficient Regression Models (JMLR 2025 · similarity 0.91)
- Scalable high-dimensional Bayesian varying coefficient models with unknown within-subject covariance (JMLR 2023 · similarity 0.89)
- A flexible empirical Bayes approach to multiple linear regression and connections with penalized regression (JMLR 2024 · similarity 0.86)
- Mesh Invaiant Infinite Dimensional Adaptive MCMC for Latent Gaussian Processes (NeurIPS 2026 · similarity 0.85)
- Bayesian Additive Distribution Regression (NeurIPS 2026 · similarity 0.85)
- Generalized Bayes for Causal Inference (NeurIPS 2026 · similarity 0.85)
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.
