Research map / Vision-language and multimodal / Human and embodied modeling
Robust Joint and Individual Variance Explained
Check 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 robust ℓ1-RJIVE instead of JIVE | joint and individual component recovery · Synthetic data, all three configurations | joint RRE: 0.5424 -> 5.5628e − 08; 0.83977 -> 8.9035e − 08; 1.3961 -> 2.427e − 07 | Helped |
| Use robust ℓ1-RJIVE instead of JIVE | joint and individual component recovery · Synthetic data, all three configurations | individual RRE: 0.93488 -> 3.5073e − 08; 1.481 -> 5.8665e − 08; 2.1977 -> 2.3743e − 06 | Helped |
| Use robust ℓ1-RJIVE instead of COBE | joint and individual component recovery · Synthetic data, all three configurations | joint RRE: 3.6403 -> 5.5628e − 08; 5.2902 -> 8.9035e − 08; 7.3973 -> 2.427e − 07 | Helped |
| Use robust ℓ1-RJIVE instead of COBE | joint and individual component recovery · Synthetic data, all three configurations | individual RRE: 1.0956 -> 3.5073e − 08; 1.0945 -> 5.8665e − 08; 1.1808 -> 2.3743e − 06 | Helped |
| Add nuclear-norm regularization to ℓ1-RJIVE | joint and individual component recovery · Synthetic data, configuration (500, 500, 500, 5, 10, 10) | joint RRE: 5.5628e − 08 -> 1.3338e − 08 | Helped |
| Add nuclear-norm regularization to ℓ1-RJIVE | joint and individual component recovery · Synthetic data, configuration (500, 500, 500, 5, 10, 10) | individual RRE: 3.5073e − 08 -> 1.1897e − 08 | Helped |
| Add nuclear-norm regularization to ℓ1-RJIVE | joint and individual component recovery · Synthetic data, configuration (1000, 1000, 1000, 10, 20, 20) | joint RRE: 8.9035e − 08 -> 9.78e − 08 | Hurt |
| Add nuclear-norm regularization to ℓ1-RJIVE | joint and individual component recovery · Synthetic data, configuration (1000, 1000, 1000, 10, 20, 20) | individual RRE: 5.8665e − 08 -> 8.9923e − 08 | Hurt |
| Add nuclear-norm regularization to ℓ1-RJIVE | joint and individual component recovery · Synthetic data, configuration (2000, 2000, 2000, 20, 40, 40) | individual RRE: 2.3743e − 06 -> 2.0574e − 07 | Helped |
| Progress faces using RJIVE rather than original images | AgeDB age-invariant verification · 5 years | accuracy: 0.609 -> 0.637 | Helped |
| Progress faces using RJIVE rather than original images | AgeDB age-invariant verification · 10 years | accuracy: 0.591 -> 0.621 | Helped |
| Progress faces using RJIVE rather than original images | AgeDB age-invariant verification · 20 years | accuracy: 0.552 -> 0.598 | Helped |
Closest papers by meaning
- Unconstrained Stochastic CCA: Unifying Multiview and Self-Supervised Learning (ICLR 2024 · similarity 0.86)
- Nonparametric Canonical Correlation Analysis (ICML 2016 · similarity 0.85)
- On Sparse Canonical Correlation Analysis (NeurIPS 2024 · similarity 0.85)
- Unpaired Canonical Correlation Analysis (NeurIPS 2026 · similarity 0.83)
- Identifiable Shared Component Analysis of Unpaired Multimodal Mixtures (NeurIPS 2024 · similarity 0.82)
- The Underlying Universal Statistical Structure of Natural Datasets (ICML 2025 · similarity 0.82)
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.