Research map / Probabilistic and scientific modeling / Dynamical systems
Revealing Common Statistical Behaviors in Heterogeneous Populations
Andrey Zhitnikov, Rotem Mulayoff, Tomer Michaeli
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 Euclidean/Riemannian averaging of subject covariances with the proposed min-over-subjects eigen-estimator (Alg. 1) | common covariance estimation · 2x2 simulated Pearson correlation estimation | bias of correlation estimate | Improved |
| Use proposed min-over-subjects eigen-estimator instead of naive averaging | common covariance estimation · 3x3 clustered noise covariance simulation | accuracy of estimated common covariance | Improved |
| Use proposed estimator instead of Euclidean/Riemannian mean on resting-state fMRI | common covariance estimation · ADHD200 fMRI, 458 control subjects | within-network correlation strength | Improved |
| Use common pdf estimator (phase/max of characteristic functions) instead of naive KDE on pooled samples | common pdf estimation · PPG and ABP joint pdf, 25 subjects | visual recovery of common pdf structure | Improved |
| Increase number of subjects with the proposed estimator | common covariance estimation · 2x2 simulated Pearson correlation estimation | bias of correlation estimate | Improved |
| Use proposed estimator instead of naive averaging at low SNR | common covariance estimation · 2x2 simulated, varying SNR | accuracy of correlation estimate | Improved |
| Proposed estimator has slightly larger variance than naive averaging | common covariance estimation · 2x2 simulated Pearson correlation estimation | variance of estimate | Hurt |
Closest papers by meaning
- Exponential Family Graphical Models: Correlated Replicates and Unmeasured Confounders, with Applications to fMRI Data (JMLR 2025 · similarity 0.87)
- Modeling Shared responses in Neuroimaging Studies through MultiView ICA (NeurIPS 2020 · similarity 0.86)
- Shared Subspace Models for Multi-Group Covariance Estimation (JMLR 2019 · similarity 0.86)
- Direct Estimation of Differential Functional Graphical Models (NeurIPS 2019 · similarity 0.86)
- Latent Variable Graphical Model Selection Using Harmonic Analysis: Applications to the Human Connectome Project (HCP) (CVPR 2016 · similarity 0.85)
- Group-Aware Matrix Estimation and Latent Subspace Recovery (NeurIPS 2026 · 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.
