Research map / Learning theory and algorithms / Matrix and tensor methods
Efficient Convex Completion of Coupled Tensors using Coupled Nuclear Norms
Kishan Wimalawarne, Hiroshi Mamitsuka
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 |
|---|---|---|---|
| replace multilinear-rank coupled norm (O,O,O) with coupled nuclear norms (ccp-1/2/3) | coupled tensor-matrix completion · Simulation, CP rank 5 tensor 20x20x20 coupled with rank 5 matrix | MSE | Improved |
| couple the tensor and matrix instead of completing each individually | coupled nuclear norms · Simulation, CP rank 5 | MSE | Improved |
| use coupled nuclear norms ccp-1 and ccp-2 instead of (O,O,O) on multilinear-rank data | coupled completion · Simulation, multilinear rank (5,5,5) tensor with rank 5 matrix | MSE | Improved |
| use coupled nuclear norms instead of the best multilinear-rank coupled norm (S,O,O) | coupled completion · UCLAF | MSE | Improved |
| use ccp-1 (whole-tensor coupled nuclear norm) versus latent-decomposition variants ccp-2 and ccp-3 (ablation) | coupled nuclear norms · UCLAF | MSE | Improved |
| couple the tensor with user-location side information using coupled nuclear norms versus SDF with CP rank 2 | coupled nuclear norms · UCLAF | MSE | Improved |
Closest papers by meaning
- A Dual Framework for Low-rank Tensor Completion (NeurIPS 2018 · similarity 0.88)
- Low-Rank Tensor Completion With a New Tensor Nuclear Norm Induced by Invertible Linear Transforms (CVPR 2019 · similarity 0.88)
- Tensor Completion Made Practical (NeurIPS 2020 · similarity 0.88)
- Tensor Ring Decomposition with Rank Minimization on Latent Space: An Efficient Approach for Tensor Completion (AAAI 2019 · similarity 0.88)
- Efficient Sparse Low-Rank Tensor Completion Using the Frank-Wolfe Algorithm (AAAI 2017 · similarity 0.87)
- Fast Tensor Completion via Approximate Richardson Iteration (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.
