The Limits of Inference in Complex Systems: When Stochastic Models Become Indistinguishable

Abstract

Robust inference for stochastic dynamical systems is often hampered by sparse sampling and the absence of closed-form likelihoods. We introduce a Monte Carlo path-inference framework that leverages full-path statistics and bridge processes to deliver reliable parameter estimation and model selection from coarsely sampled time series, without requiring analytical solutions. Crucially, we couple mechanistic stochastic models with their inference procedures to quantify how experimental design -specifically, sampling frequency and dataset size- governs estimator precision and model distinguishability. This analysis reveals optimal sampling regimes and sharp, resolution-dependent limits beyond which competing models become empirically indistinguishable. We validate the approach across four disparate systems -trajectories of optically trapped particles, human microbiome dynamics, social-media topic mentions, and forest population time series- recovering parameters and identifying when inference is fundamentally constrained by measurement resolution, thereby clarifying ongoing debates about dominant noise sources in these systems. Together, these results establish path-based Monte Carlo as a practical, general tool for inference and model discrimination in complex systems and provide principled guidelines for designing measurements that maximize information under real-world constraints.

References in corpus (34)

• Epidemic processes in complex networks
• The spread of epidemic disease on networks
• Approximate Bayesian computation scheme for parameter inference and model selection in dynamical systems
• Universally Sloppy Parameter Sensitivities in Systems Biology
• Highly comparative time-series analysis: The empirical structure of time series and their methods
• Nonequilibrium Markov processes conditioned on large deviations
• Community Detection as an Inference Problem
• Nonequilibrium microcanonical and canonical ensembles and their equivalence
• Statistical Mechanics of Ecological Systems: Neutral Theory and Beyond
• Predictability: Can the turning point and end of an expanding epidemic be precisely forecast?
• Network reconstruction and community detection from dynamics
• Integration of Langevin Equations with Multiplicative Noise and Viability of Field Theories for Absorbing Phase Transitions
• A Bayesian machine scientist to aid in the solution of challenging scientific problems
• Maximum a Posteriori Estimators as a Limit of Bayes Estimators
• Transitions across Melancholia States in a Climate Model: Reconciling the Deterministic and Stochastic Points of View
• Brownian motion in a non-homogeneous force field and photonic force microscope
• Learning force fields from stochastic trajectories
• Bayesian estimates of free energies from nonequilibrium work data in the presence of instrument noise
• A simple unified view of branching process statistics: random walks in balanced logarithmic potentials
• Generating Transition Paths by Langevin Bridges
• Heating and Cooling are Fundamentally Asymmetric and Evolve Along Distinct Pathways
• Six Susceptible-Infected-Susceptible Models on Scale-free Networks
• Martingales for physicists: A treatise on stochastic thermodynamics and beyond
• Fundamental limits to learning closed-form mathematical models from data
• Building general Langevin models from discrete data sets
• Multiplex decomposition of non-Markovian dynamics and the hidden layer reconstruction problem
• Boosting Bayesian Parameter Inference of Nonlinear Stochastic Differential Equation Models by Hamiltonian Scale Separation
• Tracking the distance to criticality in systems with unknown noise
• Endemic infectious states below the epidemic threshold and beyond herd immunity
• Neutral Theory for competing attention in social networks
• A unified perspective on exponential tilt and bridge algorithms for rare trajectories of discrete Markov processes
• Growth-rate distributions of gut microbiota time series
• Biased versus unbiased numerical methods for stochastic simulations
• Rejection-free quantum Monte Carlo in continuous time from transition path sampling