Inference of stochastic time series with missing data

Abstract

Inferring dynamics from time series is an important objective in data analysis. In particular, it is challenging to infer stochastic dynamics given incomplete data. We propose an expectation maximization (EM) algorithm that iterates between alternating two steps: E-step restores missing data points, while M-step infers an underlying network model of restored data. Using synthetic data generated by a kinetic Ising model, we confirm that the algorithm works for restoring missing data points as well as inferring the underlying model. At the initial iteration of the EM algorithm, the model inference shows better model-data consistency with observed data points than with missing data points. As we keep iterating, however, missing data points show better model-data consistency. We find that demanding equal consistency of observed and missing data points provides an effective stopping criterion for the iteration to prevent overshooting the most accurate model inference. Armed with this EM algorithm with this stopping criterion, we infer missing data points and an underlying network from a time-series data of real neuronal activities. Our method recovers collective properties of neuronal activities, such as time correlations and firing statistics, which have previously never been optimized to fit.

References in corpus (29)

• Weak pairwise correlations imply strongly correlated network states in a neural population
• Direct-coupling analysis of residue co-evolution captures native contacts across many protein families
• High-dimensional Ising model selection using ${\ell }_1$-regularized logistic regression
• Maximum entropy models for antibody diversity
• Searching for collective behavior in a network of real neurons
• Inverse statistical problems: from the inverse Ising problem to data science
• Inverse Ising inference using all the data
• How pairwise coevolutionary models capture the collective residue variability in proteins
• Prediction of spatio-temporal patterns of neural activity from pairwise correlations
• Small-correlation expansions for the inverse Ising problem
• Mean Field Theory For Non-Equilibrium Network Reconstruction
• The Bethe approximation for solving the inverse Ising problem: a comparison with other inference methods
• Searching for collective behavior in a small brain
• Statistical mechanics of the US Supreme Court
• Pseudolikelihood Decimation Algorithm Improving the Inference of the Interaction Network in a General Class of Ising Models
• The Effect of Nonstationarity on Models Inferred from Neural Data
• Maximum likelihood reconstruction for Ising models with asynchronous updates
• Learning and inference in a nonequilibrium Ising model with hidden nodes
• Market structure explained by pairwise interactions
• Network inference using asynchronously updated kinetic Ising Model
• Parameters estimation for spatio-temporal maximum entropy distributions: application to neural spike trains
• Spatio-temporal spike trains analysis for large scale networks using maximum entropy principle and Monte-Carlo method
• Network Inference with Hidden Units
• Belief-Propagation and replicas for inference and learning in a kinetic Ising model with hidden spins
• Inferring hidden states in a random kinetic Ising model: replica analysis
• Causality inference in stochastic systems from neurons to currencies: Profiting from small sample size
• Data-driven inference of hidden nodes in networks
• Inference of the sparse kinetic Ising model using the decimation method
• Inference of the Kinetic Ising Model with Heterogeneous Missing Data