Research map / Probabilistic and scientific modeling / Variational and generative sampling
Shared Independent Component Analysis for Multi-Subject Neuroimaging
Hugo Richard, Pierre Ablin, Bertrand Thirion, Alexandre Gramfort, Aapo Hyvarinen
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 |
|---|---|---|---|
| Correct Multiset CCA's sampling-noise rotation with joint diagonalization | Multiset CCA / ShICA-J · Synthetic Gaussian-component separation | Amari distance | Improved |
| Use a non-Gaussian mixture likelihood in addition to noise diversity | ShICA-ML · Synthetic hybrid Gaussian and non-Gaussian separation | Amari distance | Improved |
| Use non-Gaussian component modeling | ShICA-ML · Synthetic non-Gaussian separation without noise diversity | Amari distance | Improved |
| Use joint diagonalization after Multiset CCA | ShICA-J · Perturbed covariance estimation | Amari distance | Improved |
| Use ShICA-ML rather than ShICA-J | ShICA · Synthetic separation with super-Gaussian components | Amari distance | Improved |
| Use ShICA-J rather than ShICA-ML | ShICA · Synthetic separation with super-Gaussian components | fitting time | Improved |
| Estimate shared components with ShICA-ML | ShICA-ML · Cam-CAN MEG repeated-stimulus trials | component distance | Improved |
| Estimate shared components with ShICA-ML | ShICA-ML · fMRI missing-subject BOLD reconstruction | R^2 | Improved |
| Use ShICA-J rather than MVICA | ShICA-J · Cam-CAN MEG repeated-stimulus trials | component distance | No clear effect |
| Use Multiset CCA instead of ShICA-J | ShICA-J · Synthetic Gaussian-component separation | Amari distance | Hurt |
| Use MVICA instead of ShICA-ML | ShICA-ML · Synthetic hybrid Gaussian and non-Gaussian separation | Amari distance | Hurt |
| Use Multiset CCA instead of ShICA-J | ShICA-J · Cam-CAN MEG repeated-stimulus trials | component distance | Mixed |
Closest papers by meaning
- Modeling Shared responses in Neuroimaging Studies through MultiView ICA (NeurIPS 2020 · similarity 0.89)
- MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data (ICML 2024 · similarity 0.85)
- Unconstrained Stochastic CCA: Unifying Multiview and Self-Supervised Learning (ICLR 2024 · similarity 0.84)
- Learning High-Order Relationships of Brain Regions (ICML 2024 · similarity 0.84)
- Unpaired Canonical Correlation Analysis (NeurIPS 2026 · similarity 0.84)
- On Sparse Canonical Correlation Analysis (NeurIPS 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.
