Accurate generation of stochastic dynamics based on multi-model Generative Adversarial Networks

Abstract

Generative Adversarial Networks (GANs) have shown immense potential in fields such as text and image generation. Only very recently attempts to exploit GANs to statistical-mechanics models have been reported. Here we quantitatively test this approach by applying it to a prototypical stochastic process on a lattice. By suitably adding noise to the original data we succeed in bringing both the Generator and the Discriminator loss functions close to their ideal value. Importantly, the discreteness of the model is retained despite the noise. As typical for adversarial approaches, oscillations around the convergence limit persist also at large epochs. This undermines model selection and the quality of the generated trajectories. We demonstrate that a simple multi-model procedure where stochastic trajectories are advanced at each step upon randomly selecting a Generator leads to a remarkable increase in accuracy. This is illustrated by quantitative analysis of both the predicted equilibrium probability distribution and of the escape-time distribution. Based on the reported findings, we believe that GANs are a promising tool to tackle complex statistical dynamics by machine learning techniques

arXiv commentMain text and appendices, 10 pages and 10 figures Updated version: citations to previous work which was not known to the authors have been added, text has been re-organized and modified accordingly; supplemental material has been moved into appendices

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Conditional Generative Adversarial Nets
• Denoising Diffusion Probabilistic Models
• Machine learning and the physical sciences
• Ensemble Adversarial Training: Attacks and Defenses
• Ensemble deep learning: A review
• Generative Adversarial Network in Medical Imaging: A Review
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Towards Principled Methods for Training Generative Adversarial Networks
• Generative adversarial networks (GAN) based efficient sampling of chemical space for inverse design of inorganic materials
• Enforcing constraints for interpolation and extrapolation in Generative Adversarial Networks
• Morphological evolution via surface diffusion learned by convolutional, recurrent neural networks: extrapolation and prediction uncertainty