# Learning the temporal evolution of multivariate densities via normalizing flows

@article{Lu2021LearningTT, title={Learning the temporal evolution of multivariate densities via normalizing flows}, author={Yubin Lu and Romit Maulik and Ting Gao and Felix Dietrich and Ioannis G. Kevrekidis and Jinqiao Duan}, journal={ArXiv}, year={2021}, volume={abs/2107.13735} }

In this work, we propose a method to learn probability distributions using sample path data from stochastic differential equations. Specifically, we consider temporally evolving probability distributions (e.g., those produced by integrating local or nonlocal FokkerPlanck equations). We analyze this evolution through machine learning assisted construction of a time-dependent mapping that takes a reference distribution (say, a Gaussian) to each and every instance of our evolving distribution. If… Expand

#### Figures from this paper

#### 2 Citations

Extracting Stochastic Governing Laws by Nonlocal Kramers-Moyal Formulas

- Mathematics
- 2021

With the rapid development of computational techniques and scientific tools, great progress of data-driven analysis has been made to extract governing laws of dynamical systems from data. Despite the… Expand

Extracting stochastic dynamical systems with $\alpha$-stable L\'evy noise from data

- Mathematics, Computer Science
- 2021

This work proposes a data-driven method to extract stochastic dynamical systems with α-stable Lévy noise from short burst data based on the properties ofα-stable distributions and approximate the drift coefficient by combining nonlocal Kramers-Moyal formulas with normalizing flows. Expand

#### References

SHOWING 1-10 OF 65 REFERENCES

Generative Ensemble-Regression: Learning Stochastic Dynamics from Discrete Particle Ensemble Observations

- Computer Science, Mathematics
- ArXiv
- 2020

A new method for inferring the governing stochastic ordinary differential equations by observing particle ensembles at discrete and sparse time instants, i.e., multiple "snapshots" is proposed, in analogy to the classic "point-regression", where the dynamics are inferred by performing regression in the Euclidean space. Expand

Solving Inverse Stochastic Problems from Discrete Particle Observations Using the Fokker-Planck Equation and Physics-informed Neural Networks

- Computer Science, Physics
- SIAM J. Sci. Comput.
- 2021

A general framework based on physics-informed neural networks (PINNs) that introduces a new loss function using the Kullback-Leibler divergence to connect the stochastic samples with the FP equation, to simultaneously learn the equation and infer the multi-dimensional PDF at all times. Expand

Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limit

- Computer Science, Mathematics
- ArXiv
- 2019

This work develops a variational inference framework for deep latent Gaussian models via stochastic automatic differentiation in Wiener space, where the variational approximations to the posterior are obtained by Girsanov (mean-shift) transformation of the standard Wiener process and the computation of gradients is based on the theory of Stochastic flows. Expand

Generator estimation of Markov jump processes

- Mathematics, Computer Science
- J. Comput. Phys.
- 2007

The purpose of this paper is to compile a catalogue of existing approaches to estimate the generator of a continuous-time Markov jump process based on incomplete data, to compare the strengths and weaknesses, and to test their performance in a series of numerical examples. Expand

Learning effective stochastic differential equations from microscopic simulations: combining stochastic numerics and deep learning

- Computer Science, Physics
- ArXiv
- 2021

This work identifies effective stochastic differential equations for coarse observables of fine-grained particleor agent-based simulations and approximate the drift and diffusivity functions in these effective SDE through neural networks, which can be thought of as effective stoChastic ResNets. Expand

Nonparametric estimation of stochastic differential equations with sparse Gaussian processes.

- Computer Science, Medicine
- Physical review. E
- 2017

This paper introduces a nonparametric method for estimating the drift and diffusion terms of SDEs from a densely observed discrete time series using a sparse Gaussian process approximation. Expand

Estimating Long-Term Behavior of Flows without Trajectory Integration: The Infinitesimal Generator Approach

- Mathematics, Computer Science
- SIAM J. Numer. Anal.
- 2013

This paper proposes to directly work with the infinitesimal generator instead of the operator, completely avoiding trajectory integration in the construction of an approximate transfer operator. Expand

Temporal Normalizing Flows

- Computer Science, Physics
- 2019

This paper extends the concept of normalizing flows to so-called temporal Normalizing Flows (tNFs) to estimate time dependent distributions, leveraging the full spatio-temporal information present in the dataset. Expand

Neural Jump Stochastic Differential Equations

- Computer Science, Mathematics
- NeurIPS
- 2019

This work introduces Neural Jump Stochastic Differential Equations that provide a data-driven approach to learn continuous and discrete dynamic behavior, i.e., hybrid systems that both flow and jump. Expand

DENSITY ESTIMATION BY DUAL ASCENT OF THE LOG-LIKELIHOOD ∗

- Mathematics
- 2010

A methodology is developed to assign, from an observed sample, a joint-probability distribution to a set of continuous variables. The algorithm proposed performs this assignment by mapping the… Expand