Research map / Learning theory and algorithms / Matrix and tensor methods
A Unified Convex Surrogate for the Schatten-p Norm
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 the MSS factorization with convex factor norms and extrapolation | MSS · MovieLens 1M | test RMSE | Helped |
| Use the MSS factorization with convex factor norms and extrapolation | MSS · MovieLens 10M | test RMSE | Helped |
| Use the MSS factorization with convex factor norms and extrapolation | MSS · Netflix | test RMSE | Helped |
| Use multiple factors with convex factor penalties and extrapolation | MSS · Synthetic matrix completion | RSRE | Helped |
| Add extrapolation-based acceleration (ablation) | MSS · Synthetic matrix completion | RSRE | Helped |
| Use continuation and extrapolation rather than the compared PALM baselines without these techniques (ablation) | BSS and MSS · Synthetic matrix completion | RSRE | Helped |
| Vary the number of factors while keeping the Schatten-p setting fixed (ablation) | MSS · Synthetic matrix completion | RSRE | No clear effect |
| Set the estimated rank d to different values (ablation) | MSS · MovieLens 10M and Netflix | test RMSE | Helped |
| Use extrapolation in MSS rather than BSS (ablation) | MSS versus BSS · MovieLens 1M, MovieLens 10M, and Netflix | time versus test RMSE | Mixed |
Closest papers by meaning
- Scalable Algorithms for Tractable Schatten Quasi-Norm Minimization (AAAI 2016 · similarity 0.93)
- A novel variational form of the Schatten-$p$ quasi-norm (NeurIPS 2020 · similarity 0.93)
- Fast exact recovery of noisy matrix from few entries: the infinity norm approach (NeurIPS 2025 · similarity 0.88)
- Generalization Analysis of Deep Non-linear Matrix Completion (ICML 2024 · similarity 0.86)
- Symmetric Matrix Completion with ReLU Sampling (ICML 2024 · similarity 0.85)
- Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time (ICLR 2024 · similarity 0.85)
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.