mlsanityData to 7 Oct 2026

Sig-Splines: universal approximation and convex calibration of time series generative models

arXiv 2307.09767 ↗First posted 19 Jul 2023cs.LG cs.AI q-fin.CPcited by 0

Not on the map. Why?

Abstract (arXiv)

We propose a novel generative model for multivariate discrete-time time series data. Drawing inspiration from the construction of neural spline flows, our algorithm incorporates linear transformations and the signature transform as a seamless substitution for traditional neural networks. This approach enables us to achieve not only the universality property inherent in neural networks but also introduces convexity in the model's parameters.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 44 references that are in the map. First posted on arXiv 19 Jul 2023.

Builds on

25 of 44 references.

References · 25

  1. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  2. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  3. 2016Density estimation using Real NVPcited by 2,029
  4. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  5. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  6. 2016An overview of gradient descent optimization algorithmscited by 1,021
  7. 2016Generative Adversarial Text to Image Synthesiscited by 735
  8. 2017Masked Autoregressive Flow for Density Estimationcited by 680
  9. 2019Neural Spline Flowscited by 590
  10. 2020Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flowscited by 142
  11. 2020Flows for simultaneous manifold learning and density estimationcited by 117
  12. 2019GANSynth: Adversarial Neural Audio Synthesiscited by 114
13 more
  1. 2019Quant GANs: Deep Generation of Financial Time Seriescited by 107
  2. 2016A Primer on the Signature Method in Machine Learningcited by 100
  3. 2020Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximatorscited by 85
  4. 2016Kernels for sequentially ordered datacited by 83
  5. 2019Deep Signature Transformscited by 75
  6. 2016Normalizing Flows on Riemannian Manifoldscited by 68
  7. 2021Sig-Wasserstein GANs for Time Series Generationcited by 60
  8. 2019Cubic-Spline Flowscited by 34
  9. 2020A Data-driven Market Simulator for Small Data Environmentscited by 34
  10. 2020Robust pricing and hedging via neural SDEscited by 21
  11. 2021Multi-Asset Spot and Option Market Simulationcited by 17
  12. 2021Deep Hedging: Learning to Remove the Drift under Trading Frictions with Minimal Equivalent Near-Martingale Measurescited by 11
  13. 2022Risk-Neutral Market Simulationcited by 2

Built on by

Not cited yet.