mlsanityData to 7 Oct 2026

Distribution estimation and change-point estimation for time series via DNN-based GANs

arXiv 2211.14577 ↗First posted 26 Nov 2022cs.LG math.ST stat.THcited by 0

Not on the map. Why?

Abstract (arXiv)

The generative adversarial networks (GANs) have recently been applied to estimating the distribution of independent and identically distributed data, and have attracted a lot of research attention. In this paper, we use the blocking technique to demonstrate the effectiveness of GANs for estimating the distribution of stationary time series. Theoretically, we derive a non-asymptotic error bound for the Deep Neural Network (DNN)-based GANs estimator for the stationary distribution of the time series. Based on our theoretical analysis, we propose an algorithm for estimating the change point in time series distribution. The two main results are verified by two Monte Carlo experiments respectively, one is to estimate the joint stationary distribution of 5-tuple samples of a 20 dimensional AR(3) model, the other is about estimating the change point at the combination of two different stationary time series. A real world empirical application to the human activity recognition dataset highlights the potential of the proposed methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 45 references that are in the map. First posted on arXiv 26 Nov 2022.

Builds on

19 of 45 references.

References · 19

  1. 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 329
  2. 2017Size-Independent Sample Complexity of Neural Networkscited by 289
  3. 2016C-RNN-GAN: Continuous recurrent neural networks with adversarial trainingcited by 132
  4. 2018How Well Generative Adversarial Networks Learn Distributionscited by 78
  5. 2017On the Discrimination-Generalization Tradeoff in GANscited by 48
  6. 2021An error analysis of generative adversarial networks for learning distributionscited by 35
  7. 2019Kernel Change-point Detection with Auxiliary Deep Generative Modelscited by 32
  8. 20192-Wasserstein Approximation via Restricted Convex Potentials with Application to Improved Training for GANscited by 32
  9. 2018Approximability of Discriminators Implies Diversity in GANscited by 28
  10. 2016Multiple-change-point detection for high dimensional time series via sparsified binary segmentationcited by 24
  11. 2022Approximation bounds for norm constrained neural networks with applications to regression and GANscited by 21
  12. 2021Generative adversarial networks in time series: A survey and taxonomycited by 20
7 more
  1. 2021On the capacity of deep generative networks for approximating distributionscited by 19
  2. 2019Deconstructing Generative Adversarial Networkscited by 15
  3. 2021A likelihood approach to nonparametric estimation of a singular distribution using deep generative modelscited by 12
  4. 2022Time-series Transformer Generative Adversarial Networkscited by 10
  5. 2018JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Netscited by 7
  6. 2021InDiD: Instant Disorder Detection via Representation Learningcited by 4
  7. 2021Non-Asymptotic Error Bounds for Bidirectional GANscited by 3

Built on by

Not cited yet.