Research map / Probabilistic and scientific modeling / Variational and generative sampling
Probabilistic Missing Value Imputation for Mixed Categorical and Ordered Data
Yuxuan Zhao, Alex Townsend, Madeleine Udell
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 EGC instead of missForest | Mixed-data single imputation · Synthetic mixed data, n=2000 | categorical imputation error: 0.68(0.01) -> 0.64(0.01) | Improved |
| Use EGC instead of missForest | Mixed-data single imputation · Synthetic mixed data, n=2000 | continuous imputation error: 2.06(0.07) -> 1.81(0.06) | Improved |
| Use EGC instead of missForest | Mixed-data single imputation · Synthetic mixed data, n=2000 | ordinal imputation error: 0.59(0.02) -> 0.50(0.02) | Improved |
| Use EGC instead of missForest | Mixed-data single imputation · Synthetic mixed data, n=10000 | categorical imputation error: 0.66(0.01) -> 0.64(0.01) | Improved |
| Use EGC instead of missForest | Mixed-data single imputation · Synthetic mixed data, n=10000 | continuous imputation error: 2.05(0.04) -> 1.81(0.04) | Improved |
| Use EGC instead of missForest | Mixed-data single imputation · Synthetic mixed data, n=10000 | ordinal imputation error: 0.52(0.02) -> 0.45(0.01) | Improved |
| Use EGC instead of missForest | Mixed-data single imputation · Synthetic mixed data, n=20000 | categorical imputation error: 0.66(0.01) -> 0.64(0.01) | Improved |
| Use EGC instead of missForest | Mixed-data single imputation · Synthetic mixed data, n=20000 | continuous imputation error: 2.04(0.04) -> 1.81(0.06) | Improved |
| Use EGC instead of missForest | Mixed-data single imputation · Synthetic mixed data, n=20000 | ordinal imputation error: 0.48(0.01) -> 0.42(0.01) | Improved |
| Use EGC multiple imputation instead of MICE | Multiple imputation of missing categorical values · Synthetic MI | cross entropy loss: 0.340 (0.004) -> 0.278 (0.039) | Improved |
| Use EGC multiple imputation instead of MICE | Multiple imputation of missing categorical values · Synthetic MI | runtime (seconds): 43 (1) -> 14 (1) | Improved |
| Increase M for categorical marginal fitting | EGC · Mixed-data imputation | imputation performance | No clear effect |
Closest papers by meaning
- Nonparametric Copula Models for Multivariate, Mixed, and Missing Data (JMLR 2024 · similarity 0.92)
- Distribution Shift in Missing Data Imputation: A Risk-Based Perspective and Importance-Weighted Correction under MAR (NeurIPS 2026 · similarity 0.85)
- Learning What Not to Impute: An Uncertainty-Aware Diffusion Framework for Meaningful Missingness (NeurIPS 2026 · similarity 0.82)
- DiffPuter: Empowering Diffusion Models for Missing Data Imputation (ICLR 2025 · similarity 0.82)
- Missing data and cluster graphs: cluster-level missingness vs variable-level missingness (NeurIPS 2026 · similarity 0.81)
- Random features models: a way to study the success of naive imputation (ICML 2024 · similarity 0.81)
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.
