Research map / Learning theory and algorithms / Matrix and tensor methods
A Dual Framework for Low-rank Tensor 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 an ℓ2-based non-sparse tensor mixture instead of the latent trace norm's sparse mixture | Tensor completion · Ribeira and Baboon | test generalization performance | Helped |
| Use the non-sparse latent trace norm formulation (TR-MM) | Tensor completion · Ribeira | test RMSE: 0.087\pm0.001 -> 0.067\pm0.001 | Helped |
| Use the non-sparse latent trace norm formulation (TR-MM) | Tensor completion · Baboon | test RMSE: 0.459\pm0.002 -> 0.121 \pm 0.001 | Helped |
| Use TR-MM rather than the strongest listed baseline | Tensor completion · Tomato | test RMSE: 0.042\pm0.001 -> 0.041\pm0.001 | Helped |
| Use TR-MM rather than the strongest listed baseline | Link prediction · FB15k-237 | test AUC: 0.821\pm0.003 -> 0.823\pm0.001 | Helped |
| Use TR-MM rather than Rprecon | Tensor completion · MovieLens10M | test RMSE: 0.831\pm0.002 -> 0.840\pm0.001 | Hurt |
| Use TR-MM rather than FFW | Tensor completion with outliers · Ribeira, x=0.05 | RMSE: 0.095 -> 0.081 | Helped |
| Use TR-MM rather than Rprecon | Link prediction with outliers · FB15k-237, x=0.05 | AUC: 0.794 -> 0.803 | Helped |
| Use TR-MM rather than baselines | Link prediction with reduced training data · FB15k-237 | test AUC | Helped |
Closest papers by meaning
- Low-rank tensor completion: a Riemannian manifold preconditioning approach (ICML 2016 · similarity 0.92)
- Efficient Nonconvex Regularized Tensor Completion with Structure-aware Proximal Iterations (ICML 2019 · similarity 0.91)
- Tensor Completion Made Practical (NeurIPS 2020 · similarity 0.91)
- Fast Tensor Completion via Approximate Richardson Iteration (ICML 2025 · similarity 0.90)
- Preconditioned Riemannian Gradient Descent Algorithm for Low-Multilinear-Rank Tensor Completion (ICML 2025 · similarity 0.90)
- Generalization Analysis of Deep Non-linear Matrix Completion (ICML 2024 · 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.