Research map / Probabilistic and scientific modeling / Dynamical systems
Gaussian Partial Information Decomposition: Bias Correction and Application to High-dimensional Data
Read the paperCheck 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 the additive ~_G-PID rather than δ_G-PID or MMI-PID | PID computation on combined independent Gaussian systems · Canonical Gaussian examples with known ground truth | agreement with ground truth | Helped |
| Restrict the optimization to jointly Gaussian distributions | ~-PID estimation · Canonical Gaussian examples, including dimensionality up to d=128 | agreement with ground truth: less than 10^{-5} | Helped |
| Add finite-sample bias correction (ablation) | ~_G-PID estimates · Bit-of-all and Fully-redundant configurations | closeness to ground-truth PID | Helped |
| Remove finite-sample bias correction (ablation) | ~_G-PID estimates · Bit-of-all and Fully-redundant configurations | closeness to ground-truth PID | Hurt |
| Use a Gaussian covariance-based estimator on Poisson data | ~_G-PID · Simulated multivariate Poisson system | agreement with discrete ~-PID ground truth | Helped |
| Analyze behaviorally relevant image-change flashes rather than non-change flashes | VISl and VISal redundancy about VISp activity · Visual Behavior Neuropixels | redundant information | Helped |
| Analyze image-change flashes rather than non-change flashes | VISl and VISal redundancy about VISp activity · Visual Behavior Neuropixels | redundancy as fraction of total mutual information | Helped |
Closest papers by meaning
- Analytically deriving Partial Information Decomposition for affine systems of stable and convolution-closed distributions (NeurIPS 2024 · similarity 0.94)
- Partial Information Decomposition via Normalizing Flows in Latent Gaussian Distributions (NeurIPS 2025 · similarity 0.90)
- Multi-Region Markovian Gaussian Process: An Efficient Method to Discover Directional Communications Across Multiple Brain Regions (ICML 2024 · similarity 0.86)
- Decomposing stimulus-specific sensory neural information via diffusion models (NeurIPS 2025 · similarity 0.85)
- Inpainting the Neural Picture: Inferring Unrecorded Brain Area Dynamics from Multi-Animal Datasets (NeurIPS 2025 · similarity 0.85)
- Learning Time-Varying Multi-Region Brain Communications via Scalable Markovian Gaussian Processes (ICML 2025 · similarity 0.85)
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.