Conditional Sig-Wasserstein GANs for Time Series Generation

Ni, Hao; Szpruch, Łukasz; Wiese, Magnus; Liao, Shujian; Xiao, Baoren

doi:10.2139/ssrn.3623086

Cited by 64 publications

(33 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A problem addressed by [53] is that long time series data streams can greatly increase the dimensionality requirements of generative modelling, which may render such approaches infeasible. To counter this problem, the authors develop a metric named Signature Wasserstein-1 (Sig-W 1 ) that captures time series models' temporal dependency and uses it as a discriminator in a time series GAN.…”

Section: Conditional Sig-wasserstein Gan (Sigcwgan) (Jun 2020)mentioning

confidence: 99%

“…The generator is capable of mapping past series and noise into future series. For a rigorous mathematical description of their method, the interested reader should consult [53].…”

Section: Conditional Sig-wasserstein Gan (Sigcwgan) (Jun 2020)mentioning

confidence: 99%

“…Wiese et al implemented a GAN to approximate financial time series in discrete-time [46]. In [53], the authors designed a decision-aware GAN that generates synthetic data and supports decision processes to financial portfolio selection of end-users.…”

Section: Data Augmentationmentioning

confidence: 99%

See 2 more Smart Citations

Generative adversarial networks in time series: A survey and taxonomy

Brophy,

Wang,

She

et al. 2021

Preprint

View full text Add to dashboard Cite

Generative adversarial networks (GANs) studies have grown exponentially in the past few years. Their impact has been seen mainly in the computer vision field with realistic image and video manipulation, especially generation, making significant advancements. While these computer vision advances have garnered much attention, GAN applications have diversified across disciplines such as time series and sequence generation. As a relatively new niche for GANs, fieldwork is ongoing to develop high quality, diverse and private time series data. In this paper, we review GAN variants designed for time series related applications. We propose a taxonomy of discrete-variant GANs and continuous-variant GANs, in which GANs deal with discrete time series and continuous time series data. Here we showcase the latest and most popular literature in this field; their architectures, results, and applications. We also provide a list of the most popular evaluation metrics and their suitability across applications. Also presented is a discussion of privacy measures for these GANs and further protections and directions for dealing with sensitive data. We aim to frame clearly and concisely the latest and state-of-the-art research in this area and their applications to real-world technologies.

show abstract

Section: Conditional Sig-wasserstein Gan (Sigcwgan) (Jun 2020)mentioning

confidence: 99%

“…The generator is capable of mapping past series and noise into future series. For a rigorous mathematical description of their method, the interested reader should consult [53].…”

Section: Conditional Sig-wasserstein Gan (Sigcwgan) (Jun 2020)mentioning

confidence: 99%

See 1 more Smart Citation

Generative adversarial networks in time series: A survey and taxonomy

Brophy,

Wang,

She

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Specifically, we first spatially flatten the spatiotemporal traffic data into a multivariate time-series. We then use a signature transformation [15,53] to convert the multi-variate time-series into a vector, which we use as the embedding, and employ vectors of the real and synthetic traffic data to compute FVD.…”

Section: Metricsmentioning

confidence: 99%

SpectraGAN

Singh

Fiore

et al. 2021

Proceedings of the 17th International Conference on Emerging Networking EXperiments and Technologies

View full text Add to dashboard Cite

City-scale spatiotemporal mobile network traffic data can support numerous applications in and beyond networking. However, operators are very reluctant to share their data, which is curbing innovation and research reproducibility. To remedy this status quo, we propose SpectraGAN, a novel deep generative model that, upon training with real-world network traffic measurements, can produce high-fidelity synthetic mobile traffic data for new, arbitrary sized geographical regions over long periods. To this end, the model only requires publicly available context information about the target region, such as population census data. SpectraGAN is an original conditional GAN design with the defining feature of generating spectra of mobile traffic at all locations of the target region based on their contextual features. Evaluations with mobile traffic measurement datasets collected by different operators in 13 cities across two European countries demonstrate that SpectraGAN can synthesize more dependable traffic than a range of representative baselines from the literature. We also show that synthetic data generated with SpectraGAN yield similar results to that with real data when used in applications like radio access network infrastructure power savings and resource allocation, or dynamic population mapping. CCS CONCEPTS• Networks → Mobile networks; • Computing methodologies → Neural networks.

show abstract

“…This is incorporated in the full architecture of a Quantum Generative Adversarial Network in Section 3. Since classical GANs are becoming an important focus in Quantitative Finance [23,6,29,42], we provide an example of application for QuGAN for volatility modelling in Section 4, hoping to bridge the gap between the Quantum Computing and the Quantitative Finance communities. For completeness, we gather a few useful results from Quantum Computing in Appendix A.…”

Section: Introductionmentioning

confidence: 99%

A Quantum Generative Adversarial Network for distributions

Assouel¹,

Jacquier²,

Kondratyev³

2021

Preprint

View full text Add to dashboard Cite

Generative Adversarial Networks are becoming a fundamental tool in Machine Learning, in particular in the context of improving the stability of deep neural networks. At the same time, recent advances in Quantum Computing have shown that, despite the absence of a fault-tolerant quantum computer so far, quantum techniques are providing exponential advantage over their classical counterparts. We develop a fully connected Quantum Generative Adversarial network and show how it can be applied in Mathematical Finance, with a particular focus on volatility modelling.

show abstract

Conditional Sig-Wasserstein GANs for Time Series Generation

Cited by 64 publications

References 18 publications

Generative adversarial networks in time series: A survey and taxonomy

Generative adversarial networks in time series: A survey and taxonomy

SpectraGAN

A Quantum Generative Adversarial Network for distributions

Contact Info

Product

Resources

About