mlsanityData to 7 Oct 2026

Sig-Wasserstein GANs for Time Series Generation

arXiv 2111.01207 ↗First posted 1 Nov 2021cs.LGcited by 60

Not on the map. Why?

Abstract (arXiv)

Synthetic data is an emerging technology that can significantly accelerate the development and deployment of AI machine learning pipelines. In this work, we develop high-fidelity time-series generators, the SigWGAN, by combining continuous-time stochastic models with the newly proposed signature W1 metric. The former are the Logsig-RNN models based on the stochastic differential equations, whereas the latter originates from the universal and principled mathematical features to characterize the measure induced by time series. SigWGAN allows turning computationally challenging GAN min-max problem into supervised learning while generating high fidelity samples. We validate the proposed model on both synthetic data generated by popular quantitative risk models and empirical financial data. Codes are available at https://github.com/SigCGANs/Sig-Wasserstein-GANs.git.

Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). Builds on 16 of its 26 references that are in the map. First posted on arXiv 1 Nov 2021.

Builds on

16 of 26 references.

References · 16

  1. 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 501
  2. 2017Are GANs Created Equal? A Large-Scale Studycited by 267
  3. 2019On Gradient Descent Ascent for Nonconvex-Concave Minimax Problemscited by 266
  4. 2017Training GANs with Optimismcited by 217
  5. 2017Cycles in adversarial regularized learningcited by 122
  6. 2019Quant GANs: Deep Generation of Financial Time Seriescited by 107
  7. 2018The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimizationcited by 98
  8. 2018Signature moments to characterize laws of stochastic processescited by 54
  9. 2020A Data-driven Market Simulator for Small Data Environmentscited by 34
  10. 2020A generative adversarial network approach to calibration of local stochastic volatility modelscited by 28
  11. 2019Deep Hedging: Learning to Simulate Equity Option Marketscited by 25
  12. 2019Generative Adversarial Networks for Financial Trading Strategies Fine-Tuning and Combinationcited by 22
4 more
  1. 2020Robust pricing and hedging via neural SDEscited by 21
  2. 2020GANs May Have No Nash Equilibriacited by 20
  3. 2019Learning stochastic differential equations using RNN with log signature featurescited by 13
  4. 2021Logsig-RNN: a novel network for robust and efficient skeleton-based action recognitioncited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 8; 2023: 16; 2024: 10; 2025: 15; 2026: 10.

60 papers.

Sort:

By area:

  1. 2023FinDiff: Diffusion Models for Financial Tabular Data Generationcited by 41
  2. 2023Non-adversarial training of Neural SDEs with signature kernel scorescited by 36
  3. 2023TSGBench: Time Series Generation Benchmarkcited by 24
  4. 2022Designing Universal Causal Deep Learning Models: The Geometric (Hyper)Transformercited by 22
  5. 2023Global universal approximation of functional input maps on weighted spacescited by 19
  6. 2021Multi-Asset Spot and Option Market Simulationcited by 17
  7. 2023TSGM: A Flexible Framework for Generative Modeling of Synthetic Time Seriescited by 16
  8. 2023PCF-GAN: generating sequential data via the characteristic function of measures on the path spacecited by 13
  9. 2023TransFusion: Generating Long, High Fidelity Time Series using Diffusion Models with Transformerscited by 13
  10. 2022Fractional SDE-Net: Generation of Time Series Data with Long-term Memorycited by 9
  11. 2023Random Fourier Signature Featurescited by 9
  12. 2024Time-Causal VAE: Robust Financial Time Series Generatorcited by 8
38 more
  1. 2025Structured Agentic Workflows for Financial Time-Series Modeling with LLMs and Reflective Feedbackcited by 8
  2. 2022Improving Astronomical Time-series Classification via Data Augmentation with Generative Adversarial Networkscited by 6
  3. 2024AIGC for Industrial Time Series: From Deep Generative Models to Large Generative Modelscited by 6
  4. 2022Continuous-time stochastic gradient descent for optimizing over the stationary distribution of stochastic differential equationscited by 4
  5. 2024Towards Controllable Time Series Generationcited by 4
  6. 2024Universal randomised signatures for generative time series modellingcited by 4
  7. 2024Efficient Training of Neural Stochastic Differential Equations by Matching Finite Dimensional Distributionscited by 4
  8. 2025WaveStitch: Flexible and Fast Conditional Time Series Generation with Diffusion Modelscited by 4
  9. 2022Deep Learning for Systemic Risk Measurescited by 3
  10. 2023Generative Modelling of L'evy Area for High Order SDE Simulationcited by 3
  11. 2025Synthetic Aircraft Trajectory Generation Using Time-Based VQ-VAEcited by 3
  12. 2025Signature Maximum Mean Discrepancy Two-Sample Statistical Testscited by 3
  13. 2025CTBench: Cryptocurrency Time Series Generation Benchmarkcited by 3
  14. 2022Risk-Neutral Market Simulationcited by 2
  15. 2023Non-parametric online market regime detection and regime clustering for multidimensional and path-dependent data structurescited by 2
  16. 2023Risk factor aggregation and stress testingcited by 2
  17. 2024GCN-DevLSTM: Path Development for Skeleton-Based Action Recognitioncited by 2
  18. 2024RHiOTS: A Framework for Evaluating Hierarchical Time Series Forecasting Algorithmscited by 2
  19. 2025A synthetic dataset of French electric load curves with temperature conditioningcited by 2
  20. 2025Distributional Adversarial Attacks and Training in Deep Hedgingcited by 2
  21. 2026MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Compositioncited by 2
  22. 2023On the causality-preservation capabilities of generative modellingcited by 1
  23. 2023Neural SDEs for Conditional Time Series Generation and the Signature-Wasserstein-1 metriccited by 1
  24. 2023Dimensionality Reduction and Dynamical Mode Recognition of Circular Arrays of Flame Oscillators Using Deep Neural Networkcited by 1
  25. 2024MCGAN: Enhancing GAN Training with Regression-Based Generator Losscited by 1
  26. 2025Uncertainty-Aware Strategies: A Model-Agnostic Framework for Robust Financial Optimization through Subsamplingcited by 1
  27. 2025L-GTA: Latent Generative Modeling for Time Series Augmentationcited by 1
  28. 2025The path to a goal: Understanding soccer possessions via path signaturescited by 1
  29. 2025Semi-Supervised Bayesian GANs with Log-Signatures for Uncertainty-Aware Credit Card Fraud Detectioncited by 1
  30. 2026Variance-Corrected Multi-Asset Equity Simulation with Hybrid Hidden Markov Marginalscited by 1
  31. 2026Generating Financial Time Series by Matching Random Convolutional Featurescited by 1
  32. 2022Learning the conditional law: signatures and conditional GANs in filtering and prediction of diffusion processescited by 0
  33. 2022Neural Langevin Dynamics: towards interpretable Neural Stochastic Differential Equationscited by 0
  34. 2023Directed Chain Generative Adversarial Networkscited by 0
  35. 2023Sig-Splines: universal approximation and convex calibration of time series generative modelscited by 0
  36. 2024Mean-Field Microcanonical Gradient Descentcited by 0
  37. 2024The Roles of Generative Artificial Intelligence in Internet of Electric Vehiclescited by 0
  38. 2025SPDEBench: An Extensive Benchmark for Learning Stochastic PDEscited by 0

50 most cited of 60 All 60 (JSON)