Diffusion learning reveals viable parameter manifolds and compensation geometry in biological dynamical systems
Abstract
Models of complex systems often have many parameters, yet are constrained by far fewer experimentally accessible observables; consequently, similar activity can emerge from coordinated parameter changes. We formalize these compatible parameter sets as \emph{viable parameter manifolds}: the inverse images of target dynamical features under a parameter-to-feature map. The relevant codimension is not the number of reported features, but the effective rank of that map at the target scale. Locally redundant features lower the effective codimension, while poor conditioning, high curvature, or regime mixing degrade learnability. We train conditional score-based diffusion models on simulated parameter--feature pairs and use them as amortized samplers of prior-weighted viable sets. In the Lorenz system, scalar trajectory statistics generate thin viable sheets, and a finite-tolerance conditioning localizes a transition-adjacent corridor. In the Izhikevich neuron model, four firing descriptors lie close to a nearly two-dimensional family of features, and the learned inverse images reveal distinct regular and irregular compensation geometries. In a deterministic ODE reduction of finite spiking networks, the same framework reveals excitatory--inhibitory compensation, timescale--coupling tradeoffs, and viable manifolds across 4--12 parameter dimensions. In this view, robustness, compensation, and hidden parameter dependencies are organized as inverse geometry, with diffusion models providing practical tools for sampling, visualizing, and interrogating that geometry.
Related
- Behavioral Mapping of Hierarchical Dynamical Models Accelerates Bayesian Parameter Inference
- Hypothesis-Driven Identification of Neural Algorithms With Dynamical Structure-Preserving Manifolds.
- MuseDrift: Navigating Protein Evolutionary Manifolds with Conditional Discrete Diffusion
- Parameter uncertainty in dynamical models: a practical identifiability index
- 2D reaction-diffusion model-based biopsy simulation for dynamic tumor growth parameter estimation
BibTeX
@misc{zhang2026diffusion,
title = {{Diffusion learning reveals viable parameter manifolds and compensation geometry in biological dynamical systems}},
author = {Ruilin Zhang and Louis Tao and Zhuo-Cheng Xiao},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2607.03671},
eprint = {2607.03671},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.03671},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - Diffusion learning reveals viable parameter manifolds and compensation geometry in biological dynamical systems
AU - Ruilin Zhang
AU - Louis Tao
AU - Zhuo-Cheng Xiao
PY - 2026
DA - 2026/09/11
PB - arXiv
DO - 10.48550/arxiv.2607.03671
UR - https://arxiv.org/abs/2607.03671
AB - Models of complex systems often have many parameters, yet are constrained by far fewer experimentally accessible observables; consequently, similar activity can emerge from coordinated parameter changes. We formalize these compatible parameter sets as \emph{viable parameter manifolds}: the inverse images of target dynamical features under a parameter-to-feature map. The relevant codimension is not the number of reported features, but the effective rank of that map at the target scale. Locally redundant features lower the effective codimension, while poor conditioning, high curvature, or regime mixing degrade learnability. We train conditional score-based diffusion models on simulated parameter--feature pairs and use them as amortized samplers of prior-weighted viable sets. In the Lorenz system, scalar trajectory statistics generate thin viable sheets, and a finite-tolerance conditioning localizes a transition-adjacent corridor. In the Izhikevich neuron model, four firing descriptors lie close to a nearly two-dimensional family of features, and the learned inverse images reveal distinct regular and irregular compensation geometries. In a deterministic ODE reduction of finite spiking networks, the same framework reveals excitatory--inhibitory compensation, timescale--coupling tradeoffs, and viable manifolds across 4--12 parameter dimensions. In this view, robustness, compensation, and hidden parameter dependencies are organized as inverse geometry, with diffusion models providing practical tools for sampling, visualizing, and interrogating that geometry.
ER -