Research map / Learning theory and algorithms / Matrix and tensor methods
Conformalized matrix completion
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 conformalized ALS intervals instead of model-based ALS intervals | ALS · Rossmann sales, heterogeneous missingness | AvgCov: 0.75 versus around $1-\alpha$ | Helped |
| Use conformalized ALS intervals instead of model-based ALS intervals | ALS · Rossmann sales, homogeneous missingness | AvgCov | Mixed |
| Use one-shot weighted conformal calibration rather than exact weighted conformal calibration (ablation) | CMC-ALS · Heterogeneous missingness, Gaussian noise, k*=12 | coverage and interval length | No clear effect |
| Estimate sampling probabilities rather than use oracle sampling probabilities (ablation) | CMC-ALS · Heterogeneous missingness, adversarial heterogeneous noise | coverage | Hurt |
| Estimate sampling probabilities rather than use oracle sampling probabilities (ablation) | CMC-ALS · Heterogeneous missingness, Gaussian or random heterogeneous noise | coverage | No clear effect |
| Misspecify the sampling model (ablation) | CMC · Random heterogeneous noise | coverage | Hurt |
| Misspecify the sampling model (ablation) | CMC · Adversarial heterogeneous noise | coverage: above 0.85 | Hurt |
Closest papers by meaning
- Scalable Completion of Nonnegative Matrix with Separable Structure (AAAI 2016 · similarity 0.90)
- A Pairwise Pseudo-likelihood Approach for Matrix Completion with Informative Missingness (NeurIPS 2024 · similarity 0.89)
- RGNMR: A Gauss-Newton method for robust matrix completion with theoretical guarantees (NeurIPS 2025 · similarity 0.89)
- Generalization Analysis of Deep Non-linear Matrix Completion (ICML 2024 · similarity 0.88)
- Symmetric Matrix Completion with ReLU Sampling (ICML 2024 · similarity 0.88)
- Matrix Completion with Incomplete Side Information via Orthogonal Complement Projection (ICML 2025 · similarity 0.87)
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.