Research map / Probabilistic and scientific modeling / Variational and generative sampling
Maximum Likelihood for Gaussian Process Classification and Generalized Linear Mixed Models under Case-Control Sampling
Omer Weissbrod, Shachar Kaufman, David Golan, Saharon Rosset
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 |
|---|---|---|---|
| account for ascertainment (AEP/APL/PCGC) instead of plain EP (ablation) | GP classification hyperparameter estimation · Linear kernel simulation (K=1%) | variance component bias | Improved |
| use AEP instead of APL/PCGC when number of features is small | hyperparameter estimation · Dimensionality sweep (m<50) | estimation accuracy: m<50 | Improved |
| use likelihood-based AEP instead of moment-based PCGC | hyperparameter estimation · Sample size sweep | sampling variance | Improved |
| use AEP under feature standardization misspecification | hyperparameter estimation · Standardization noise sweep (e in [0,1]) | robustness | Improved |
| use AEP instead of APL/PCGC/plain EP with RBF kernel | hyperparameter estimation · RBF kernel simulation | estimation bias: -0.016 and 0.022 vs bias >0.2 and >0.15 | Improved |
| use AEP instead of plain EP for latent variable inference | latent variable posterior · Real GWAS data | case-control separation | Improved |
| use AEP instead of APL/PCGC | computation · Runtime scaling | runtime: cubic vs quadratic in sample size | Hurt |
Closest papers by meaning
- Decomposing feature-level variation with Covariate Gaussian Process Latent Variable Models (ICML 2019 · similarity 0.85)
- Gaussian Graphical Model Exploration and Selection in High Dimension Low Sample Size Setting (TPAMI 2020 · similarity 0.85)
- Penalized Maximum Likelihood Estimation of Multi-layered Gaussian Graphical Models (JMLR 2016 · similarity 0.84)
- High-Dimensional Inference for Cluster-Based Graphical Models (JMLR 2020 · similarity 0.84)
- Continuous Bayesian Model Selection for Multivariate Causal Discovery (ICML 2025 · similarity 0.83)
- Learning from Summarized Data: Gaussian Process Regression with Sample Quasi-Likelihood (AAAI 2025 · similarity 0.83)
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.
