Sig‐Wasserstein GANs for conditional time series generation
From MaRDI portal
Publication:6196300
Abstract: Generative adversarial networks (GANs) have been extremely successful in generating samples, from seemingly high dimensional probability measures. However, these methods struggle to capture the temporal dependence of joint probability distributions induced by time-series data. Furthermore, long time-series data streams hugely increase the dimension of the target space, which may render generative modeling infeasible. To overcome these challenges, we integrate GANs with mathematically principled and efficient path feature extraction called the signature of a path. The signature of a path is a graded sequence of statistics that provides a universal description for a stream of data, and its expected value characterizes the law of the time-series model. In particular, we a develop new metric, (conditional) Sig-, that captures the (conditional) joint law of time series models, and use it as a discriminator. The signature feature space enables the explicit representation of the proposed discriminators which alleviates the need for expensive training. Furthermore, we develop a novel generator, called the conditional AR-FNN, which is designed to capture the temporal dependence of time series and can be efficiently trained. We validate our method on both synthetic and empirical datasets and observe that our method consistently and significantly outperforms state-of-the-art benchmarks with respect to measures of similarity and predictive ability.
Recommendations
- Quant GANs: deep generation of financial time series
- Fin-GAN: forecasting and classifying financial time series via generative adversarial networks
- Monte Carlo simulation of SDEs using GANs
- GANs training: A game and stochastic control approach
- Wasserstein autoregressive models for density time series
Cites work
- scientific article; zbMATH DE number 42272 (Why is no real title available?)
- A continuous-time GARCH process driven by a Lévy process: stationarity and second-order behaviour
- Analysis of Financial Time Series
- Characteristic functions of measures on geometric rough paths
- Cycles in adversarial regularized learning
- Developing the Path Signature Methodology and Its Application to Landmark- Based Human Action Recognition
- Expected signature of Brownian motion up to the first exit time from a bounded domain
- Expected signature of stopped Brownian motion on \(d\)-dimensional \(C^{2, \alpha }\)-domains has finite radius of convergence everywhere: \(2 \leq d \leq 8\)
- Functional linear regression with truncated signatures
- Generative adversarial networks for financial trading strategies fine-tuning and combination
- On the signature and cubature of the fractional Brownian motion for \(H > \frac{1}{2}\)
- The expected signature of Brownian motion stopped on the boundary of a circle has finite radius of convergence
- The uniqueness of signature problem in the non-Markov setting
- Uniqueness for the signature of a path of bounded variation and the reduced path group
Cited in
(4)
This page was built for publication: Sig‐Wasserstein GANs for conditional time series generation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6196300)
