Generative Adversarial Network for Probabilistic Forecast of Random Dynamical System
Not on the map. Why?
Abstract (arXiv)
We present a deep learning model for data-driven simulations of random dynamical systems without a distributional assumption. The deep learning model consists of a recurrent neural network, which aims to learn the time marching structure, and a generative adversarial network (GAN) to learn and sample from the probability distribution of the random dynamical system. Although GANs provide a powerful tool to model a complex probability distribution, the training often fails without a proper regularization. Here, we propose a regularization strategy for a GAN based on consistency conditions for the sequential inference problems. First, the maximum mean discrepancy (MMD) is used to enforce the consistency between conditional and marginal distributions of a stochastic process. Then, the marginal distributions of the multiple-step predictions are regularized by using MMD or from multiple discriminators. The behavior of the proposed model is studied by using three stochastic processes with complex noise structures.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 26 of its 57 references that are in the map. First posted on arXiv 4 Nov 2021.
Builds on
26 of 57 references.
References · 26
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
- 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
- 2014Conditional Generative Adversarial Netscited by 2,162
- 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 2,018
- 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
- 2017Deep learning for universal linear embeddings of nonlinear dynamicscited by 494
- 2020Time Series Forecasting With Deep Learning: A Surveycited by 459
- 2016SeqGAN: Sequence Generative Adversarial Nets with Policy Gradientcited by 376
- 2015A Recurrent Latent Variable Model for Sequential Datacited by 362
- 2018Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networkscited by 155
- 2019High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processescited by 148
14 more
- 2020Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flowscited by 144
- 2019Consistency Regularization for Generative Adversarial Networkscited by 136
- 2018Physics-Informed Generative Adversarial Networks for Stochastic Differential Equationscited by 135
- 2017Stabilizing Training of Generative Adversarial Networks through Regularizationcited by 118
- 2018Data Driven Governing Equations Approximation Using Deep Neural Networkscited by 96
- 2017Gradient descent GAN optimization is locally stablecited by 67
- 2017Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multi-Layer Calorimeterscited by 55
- 2017Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Stepcited by 45
- 2020Quantum State Tomography with Conditional Generative Adversarial Networkscited by 41
- 2019Enforcing Statistical Constraints in Generative Adversarial Networks for Modeling Chaotic Dynamical Systemscited by 33
- 2021Disentangled Recurrent Wasserstein Autoencodercited by 22
- 2020Towards a Better Global Loss Landscape of GANscited by 17
- 2018Deep learning algorithm for data-driven simulation of noisy dynamical systemcited by 12
- 2020Variational inference formulation for a model-free simulation of a dynamical system with unknown parameters by a recurrent neural networkcited by 2
Built on by
Citing papers per year: 2023: 2.
2 papers.