Research map / Learning theory and algorithms / Matrix and tensor methods
New Perspectives on k-Support and Cluster Norms
Andrew M. McDonald, Massimiliano Pontil, Dimitris Stamos
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 |
|---|---|---|---|
| use the spectral k-support norm instead of the trace norm | regularized low rank matrix completion · matrix completion (synthetic and real datasets) | test error | Improved |
| center the spectral k-support norm (regularize W times the centering projection) | spectral k-support norm · multitask learning | test error | Improved |
| add a final thresholding step on singular values selected by training error | box-norm regularized matrix completion · experiments 2, 3 and 4 | test error | Improved |
Closest papers by meaning
- Iterative Regularization with k-support Norm: An Important Complement to Sparse Recovery (AAAI 2024 · similarity 0.85)
- Matrix Norms in Data Streams: Faster, Multi-Pass and Row-Order (ICML 2018 · similarity 0.85)
- The Sample Complexity of One-Hidden-Layer Neural Networks (NeurIPS 2022 · similarity 0.85)
- Factor Group-Sparse Regularization for Efficient Low-Rank Matrix Recovery (NeurIPS 2019 · similarity 0.85)
- Optimal Rates for Vector-Valued Spectral Regularization Learning Algorithms (NeurIPS 2024 · similarity 0.84)
- Optimal Sketching for Residual Error Estimation for Matrix and Vector Norms (ICLR 2024 · similarity 0.84)
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.
