Research map / Learning theory and algorithms / Matrix and tensor methods
Empirical Bayes Matrix Factorization
Wei Wang, Matthew Stephens
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 |
|---|---|---|---|
| use flash (empirical Bayes) instead of other sparse factor methods | rank-1 simulation n=200 p=300 · single-factor simulation (sparsity 0.9, 0.3, 0) | RRMSE | Improved |
| use flash instead of softImpute in non-sparse loading case | rank-1 simulation · single-factor simulation (no sparsity) | RRMSE | No clear effect |
| use flash instead of SSVD | rank-1 simulation · single-factor simulation | RRMSE | Improved |
| use flash on sparse bi-cluster rank-3 data | flash vs softImpute, SSVD, PMD · bi-cluster simulation (n=150, p=240, K=3, 100 replicates) | RRMSE | Improved |
| tune PMD and softImpute by cross-validation instead of defaults (ablation) | PMD, softImpute · missing data imputation, five real datasets | RMSE | Improved |
| use flash instead of cross-validated PMD.cv1 and SI.cv | flash · missing data imputation, five real datasets | RMSE | No clear effect |
| use flash instead of NBSFA | flash · missing data imputation, five real datasets | RMSE | Improved |
| use scale mixture of normals prior instead of point-normal prior (ablation) | flash · GTEx imputation | RMSE | Hurt |
| use scale mixture of normals prior instead of point-normal prior (ablation) | flash · other four imputation datasets and simulations | RMSE | No clear effect |
| use flash sparse factors instead of softImpute nuclear-norm factors | GTEx eQTL · GTEx factor interpretability | interpretability | Improved |
Closest papers by meaning
- Covariate-moderated Empirical Bayes Matrix Factorization (NeurIPS 2025 · similarity 0.92)
- Bayesian group factor analysis with structured sparsity (JMLR 2016 · similarity 0.89)
- A Particle-Based Variational Approach to Bayesian Non-negative Matrix Factorization (JMLR 2019 · similarity 0.87)
- A flexible empirical Bayes approach to multiple linear regression and connections with penalized regression (JMLR 2024 · similarity 0.86)
- Sparse encoding for more-interpretable feature-selecting representations in probabilistic matrix factorization (ICLR 2021 · similarity 0.86)
- Efficient Sparse PCA via Block-Diagonalization (ICLR 2025 · 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.
