Research map / Learning theory and algorithms / Sample complexity
Factor-analytic inverse regression for high-dimension, small-sample dimensionality reduction
Aditi Jha, Michael J. Morais, Jonathan W Pillow
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 |
|---|---|---|---|
| add smoothness prior (sCFAD vs CFAD) (ablation) | CFAD on fMRI visual object recognition · Haxby fMRI 8-class, Table 1 | classification accuracy (%): +5.1 on subject 1 (62.4 vs 57.3); improves on all six subjects | Improved |
| add smoothness prior (sCFAD vs CFAD) (ablation) | CFAD on HCP working memory task · HCP working memory 4-class, Table 3 | classification accuracy (%): sCFAD higher than CFAD on all 10 subjects (e.g. 73.9 vs 70.9 on subject 1) | Improved |
| use CFAD/sCFAD instead of baselines | fMRI visual object recognition · Haxby fMRI 8-class, Table 1 | classification accuracy (%): sCFAD 71.8 vs best baseline DR 62.3 on subject 2 | Improved |
| use sCFAD instead of baselines (HCP) | HCP working memory task · HCP working memory 4-class, Table 3 | classification accuracy (%): sCFAD loses to LOL on subject 1 (73.9 vs 72.7 is a win; others) and sCFAD best on 9 of 10 subjects | Mixed |
| CFAD (no smoothness) vs DR on fMRI visual recognition | CFAD on fMRI visual object recognition · Haxby fMRI 8-class, Table 1 | classification accuracy (%): CFAD 70.9 vs DR 71.9 on subject 6; CFAD beats DR on 4 of 6 subjects | Mixed |
| Standard inverse regression SDR methods (SIR, SAVE, DR, LAD) applied in N<p regime | SIR/SAVE/DR on fMRI and HCP · HCP working memory | feasibility | Hurt |
Closest papers by meaning
- The Maximum Separation Subspace in Sufficient Dimension Reduction with Categorical Response (JMLR 2020 · similarity 0.87)
- Enhancing Sufficient Dimension Reduction via Hellinger Correlation (ICML 2024 · similarity 0.86)
- Neural Networks Perform Sufficient Dimension Reduction (AAAI 2025 · similarity 0.85)
- Random-projection ensemble dimension reduction (ICLR 2026 · similarity 0.85)
- Kernel Sufficient Dimension Reduction and Variable Selection for Compositional Data via Amalgamation (ICML 2023 · similarity 0.85)
- Deep Principal Support Vector Machines for Nonlinear Sufficient Dimension Reduction (ICML 2025 · similarity 0.83)
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.
