stat.MLOct 30, 2024

Identifying Drift, Diffusion, and Causal Structure from Temporal Snapshots

Authors: Vincent Guan, Joseph Janssen, Hossein Rahmani, Andrew Warren, Stephen Zhang, Elina Robeva, Geoffrey Schiebinger

Organizations: Department of Mathematics University of British Columbia, Vancouver, Canada · Department of Earth, Ocean and Atmospheric Sciences University of British Columbia, Vancouver, Canada · School of Mathematics and Statistics University of Melbourne, Melbourne, Australia

Abstract

Stochastic differential equations (SDEs) are a fundamental tool for modelling dynamic processes, including gene regulatory networks (GRNs), contaminant transport, financial markets, and image generation. However, learning the underlying SDE from data is a challenging task, especially if individual trajectories are not observable. Motivated by burgeoning research in single-cell datasets, we present the first comprehensive approach for jointly identifying the drift and diffusion of an SDE from its temporal marginals. Assuming linear drift and additive diffusion, we show that non-identifiability can only arise if the initial distribution possesses generalized rotational symmetries. We further prove that even if this condition holds, the drift and diffusion can almost always be recovered from the marginals. Additionally, we show that the causal graph of any SDE with additive diffusion can be recovered from the identified SDE parameters. To complement this theory, we adapt entropy-regularized optimal transport to handle anisotropic diffusion and introduce APPEX (Alternating Projection Parameter Estimation from X0X_0), an iterative algorithm designed to estimate the drift, diffusion, and causal graph of an additive noise SDE, solely from temporal marginals, and demonstrate its effectiveness on simulated data from linear additive noise SDEs.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts

    Jun 26, 2026Yuanyuan Wang, Wenjie Wang, Haoxuan Li +2Stochastic Differential EquationsCausal Representation Learning

  2. Identifiability from Stationary Covariance in Linear SDEs with Reciprocal Interactions and Latent Variables

    Oct 22, 2026Ana Leticia Garcez Vicente, Saber SalehkaleybarCausal IdentifiabilityStochastic Differential Equations

  3. Non-parametric recovery of causal diffusion mechanisms from steady-state observations

    Jun 29, 2026Richard Schwank, Mathias DrtonStochastic Differential EquationsCausal Identifiability