Temporal Normalizing Flows
arXiv:1912.09092
Abstract
Analyzing and interpreting time-dependent stochastic data requires accurate and robust density estimation. In this paper we extend 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. Our approach is unsupervised, does not require an a-priori characteristic scale and can accurately estimate multi-scale distributions of vastly different length scales. We illustrate tNFs on sparse datasets of Brownian and chemotactic walkers, showing that the inclusion of temporal information enhances density estimation. Finally, we speculate how tNFs can be applied to fit and discover the continuous PDE underlying a stochastic process.
References in corpus (10)
- Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
- Density estimation using Real NVP
- Neural Ordinary Differential Equations
- Inferring solutions of differential equations using noisy multi-fidelity data
- Masked Autoregressive Flow for Density Estimation
- DeepMoD: Deep learning for Model Discovery in noisy data
- FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
- A Review of Kernel Density Estimation with Applications to Econometrics
- Gaussian Process Prior Variational Autoencoders
- Unconstrained Monotonic Neural Networks
Cited by in corpus (4)
- Equivariant flow-based sampling for lattice gauge theory
- Solving time dependent Fokker-Planck equations via temporal normalizing flow
- Learning the temporal evolution of multivariate densities via normalizing flows
- Charting Galactic Accelerations: When and How to Extract a Unique Potential from the Distribution Function