Research map / Learning theory and algorithms / Matrix and tensor methods
Optimal Discrete 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 |
|---|---|---|---|
| learn discrete thresholds jointly (ODMC) instead of RDMC | ODMC · MovieLens 1M | RMSE: 0.9870 -> 0.9371 | Helped |
| ODMC instead of RDMC | ODMC · MovieLens 100k | RMSE: 0.9709 -> 0.9679 | No clear effect |
| ODMC instead of RDMC | ODMC · YouTube Shared Subscribers | MAE: 0.7884 -> 0.7368 | Helped |
| ODMC instead of RDMC | ODMC · YouTube Shared Favorite Videos | RMSE: 2.2244 -> 2.1463 | Helped |
| ODMC instead of RDMC | ODMC · YouTube Shared Subscriptions | MAE: 0.5916 -> 0.5257 | Helped |
| ODMC (joint thresholds) instead of OPTSPACE with tuned threshold | ODMC · MovieLens 1M | RMSE: 0.9402 -> 0.9371 | Helped |
| ODMC instead of OPTSPACE with tuned threshold | ODMC · MovieLens 100k | RMSE: 0.9622 -> 0.9679 | Hurt |
| ODMC instead of RankK with tuned threshold | ODMC · YouTube Shared Subscribers | RMSE: 1.6137 -> 1.6206 | No clear effect |
| ODMC instead of RankK with tuned threshold | ODMC · YouTube Shared Subscriptions | MAE: 0.5055 -> 0.5257 | Hurt |
| ODMC instead of SVD plus threshold tuning | ODMC · YouTube Shared Subscribers | RMSE: 1.9612 -> 1.6206 | Helped |
Closest papers by meaning
- Mixture Matrix Completion (NeurIPS 2018 · similarity 0.89)
- Matrix Completion has No Spurious Local Minimum (NeurIPS 2016 · similarity 0.89)
- Generalization Bounds for Semi-supervised Matrix Completion with Distributional Side Information (AAAI 2026 · similarity 0.88)
- Online Matrix Completion: A Collaborative Approach with Hott Items (ICML 2024 · similarity 0.88)
- Multi-Label Ranking Loss Minimization for Matrix Completion (AAAI 2025 · similarity 0.87)
- Recommendations with Sparse Comparison Data: Provably Fast Convergence for Nonconvex Matrix Factorization (ICML 2025 · similarity 0.86)
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.