Mixture Density Conditional Generative Adversarial Network Models (MD-CGAN)

Generative Adversarial Networks (GANs) have gained significant attention in recent years, with impressive applications highlighted in computer vision in particular. Compared to such examples, however, there have been more limited applications of GANs to time series modelling, including forecasting. In this work, we present the Mixture Density Conditional Generative Adversarial Model (MD-CGAN), with a focus on time series forecasting. We show that our model is capable of estimating a probabilistic posterior distribution over forecasts and that, in comparison to a set of benchmark methods, the MD-CGAN model performs well, particularly in situations where noise is a significant component of the observed time series. Further, by using a Gaussian mixture model as the output distribution, MD-CGAN offers posterior predictions that are non-Gaussian.

[1]  H. M. Douty,et al.  United States Department of Labor , 2020, Encyclopedia of Behavioral Medicine.

[2]  Gerhard Widmer,et al.  Mixture Density Generative Adversarial Networks , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[4]  G. G. Stokes "J." , 1890, The New Yale Book of Quotations.

[5]  Kumar Vijay Mishra,et al.  Joint Multi-Layer GAN-Based Design of Tensorial RF Metasurfaces , 2019, 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP).

[6]  Gunnar Rätsch,et al.  Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs , 2017, ArXiv.

[7]  Robert C. N. Pilawa-Podgurski,et al.  Design and control of a GaN-based, 13-level, flying capacitor multilevel inverter , 2016, 2016 IEEE 17th Workshop on Control and Modeling for Power Electronics (COMPEL).

[8]  Mihaela van der Schaar,et al.  Time-series Generative Adversarial Networks , 2019, NeurIPS.

[9]  Ravi Kiran Sarvadevabhatla,et al.  DeLiGAN: Generative Adversarial Networks for Diverse and Limited Data , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Pourya Assem,et al.  Design and Control of a GaN-Based, 13-Level, Flying Capacitor Multilevel Inverter , 2020, IEEE Journal of Emerging and Selected Topics in Power Electronics.

[11]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[12]  Daphna Weinshall,et al.  Gaussian Mixture Generative Adversarial Networks for Diverse Datasets, and the Unsupervised Clustering of Images , 2018, ArXiv.

[13]  Yair Weiss,et al.  On GANs and GMMs , 2018, NeurIPS.

[14]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[15]  Zhisong Pan,et al.  Stock Market Prediction on High-Frequency Data Using Generative Adversarial Nets , 2018 .

[16]  Bing Ji,et al.  Design and control of a bidirectional wireless charging system using GaN devices , 2019, 2019 IEEE Applied Power Electronics Conference and Exposition (APEC).

[17]  L. Glass,et al.  Oscillation and chaos in physiological control systems. , 1977, Science.

[18]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[19]  Ying Zhang,et al.  Multivariate Time Series Imputation with Generative Adversarial Networks , 2018, NeurIPS.

[20]  Yang Yu,et al.  Mixture of GANs for Clustering , 2018, IJCAI.

[21]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[22]  Magnus Wiese,et al.  Quant GANs: deep generation of financial time series , 2019, Quantitative Finance.