Feature leakage and the identifiability of direct-dependency entropy models of neural activity
- 1Kempner Institute for the Study of Natural and Artificial Intelligence at Harvard University
- 2Department of Neurobiology , Howard Hughes Medical Institute , Harvard Medical School
Abstract
Biological neurons receive thousands of synaptic inputs on branching, electrically excitable dendrites, yet population activity is often modeled with direct input-output rules in which each input contributes independently to a scalar drive. We study what successful prediction by such models does, and does not, reveal about neural computation. For conditional maximum-entropy models that match output rates and pairwise output-input coactivities, the entropy explained by a direct model is a prediction measure under the sampled input distribution, not a mechanism-identification test. A restricted MaxEnt fit is an information projection: omitted interaction, temporal, or hidden-state terms can be absorbed into fitted first-order parameters whenever they are correlated with the included sufficient statistics. For sparse correlated binary inputs, this absorption has an explicit coskewness form. We introduce diagnostics that separate in-distribution prediction from recovery of the response rule: state reweighting that holds P(y|x) fixed while changing P(x), conditional log-odds contrasts for local additivity, and temporal leakage controls. In ground-truth simulations, purely higher-order responses can pass first-order entropy and raw coactivity tests under leakage-prone sampling, but are correctly classified after reweighting. Applied to selected, leakage-enriched local tables from CA1 hippocampal recordings, approximately half of tables that appear first-order under empirical weights become distribution-sensitive under balanced reweighting, far above a matched additive-surrogate null. Thus direct entropy-explained fractions and raw coactivity predictions should be interpreted as predictions under the observed state distribution, not as evidence that mechanisms outside the direct model are absent or small.
Related
- A dependency-free, streamable format and cross-language toolkit for scalable LC-MS feature detection: reading only what you need
- A feature-optimized EEG framework using multiscale entropy and metaheuristic optimization for cognitive analysis.
- Benchmark validity in graph neural network scoring of metabolic reaction activity on Recon3D: detecting label leakage, memorized noise and input-invariant models
- Frequency and Laminar Profile of Feature Specific Visual Activity Revealed by Interleaved EEG-fMRI
- Compact target-aware stability-based feature selection for cross-dataset wearable activity monitoring
BibTeX
@misc{safaai2026feature,
title = {{Feature leakage and the identifiability of direct-dependency entropy models of neural activity}},
author = {Houman Safaai and Bernardo Luis Sabatini},
howpublished = {arXiv (Cornell University)},
year = {2026},
month = jun,
doi = {10.48550/arxiv.2606.01661},
url = {https://arxiv.org/abs/2606.01661},
note = {CC BY},
}
RIS
TY - UNPB
TI - Feature leakage and the identifiability of direct-dependency entropy models of neural activity
AU - Houman Safaai
AU - Bernardo Luis Sabatini
PY - 2026
DA - 2026/06/01
PB - arXiv (Cornell University)
DO - 10.48550/arxiv.2606.01661
UR - https://arxiv.org/abs/2606.01661
AB - Biological neurons receive thousands of synaptic inputs on branching, electrically excitable dendrites, yet population activity is often modeled with direct input-output rules in which each input contributes independently to a scalar drive. We study what successful prediction by such models does, and does not, reveal about neural computation. For conditional maximum-entropy models that match output rates and pairwise output-input coactivities, the entropy explained by a direct model is a prediction measure under the sampled input distribution, not a mechanism-identification test. A restricted MaxEnt fit is an information projection: omitted interaction, temporal, or hidden-state terms can be absorbed into fitted first-order parameters whenever they are correlated with the included sufficient statistics. For sparse correlated binary inputs, this absorption has an explicit coskewness form. We introduce diagnostics that separate in-distribution prediction from recovery of the response rule: state reweighting that holds P(y|x) fixed while changing P(x), conditional log-odds contrasts for local additivity, and temporal leakage controls. In ground-truth simulations, purely higher-order responses can pass first-order entropy and raw coactivity tests under leakage-prone sampling, but are correctly classified after reweighting. Applied to selected, leakage-enriched local tables from CA1 hippocampal recordings, approximately half of tables that appear first-order under empirical weights become distribution-sensitive under balanced reweighting, far above a matched additive-surrogate null. Thus direct entropy-explained fractions and raw coactivity predictions should be interpreted as predictions under the observed state distribution, not as evidence that mechanisms outside the direct model are absent or small.
SN - 2331-8422
ER -