Deep Factors with Gaussian Processes for Forecasting

By Danielle C. Maddix, Bernie Wang, Alex Smola. 2018

47 citations recorded by the source corpus.

A large collection of time series poses significant challenges for classical and neural forecasting approaches. Classical time series models fail to fit data well and to scale to large problems, but succeed at providing uncertainty estimates. The converse is true for deep neural networks. In this paper, we propose a hybrid model that incorporates the benefits of both approaches. Our new method is data-driven and scalable via a latent, global, deep component. It also handles uncertainty through a local classical Gaussian Process model. Our experiments demonstrate that our method obtains higher accuracy than state-of-the-art methods.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Mingsheng Long
2. Jianmin Wang
3. Haixu Wu
4. Yu-Xiang Wang
5. Jan Gasthaus
6. Tim Januschowski
7. Bernie Wang
8. Kate Saenko

In Computer Vision and Pattern Recognition

1. Mingsheng Long
2. Jianmin Wang
3. Dacheng Tao
4. Luc Van Gool
5. Jiashi Feng
6. Trevor Darrell
7. Yi Yang
8. Kate Saenko

In Signal Processing

1. Mingsheng Long
2. Haixu Wu
3. Jianmin Wang
4. Bernie Wang
5. Tim Januschowski
6. Jan Gasthaus
7. Syama Sundar Rangapuram
8. Danielle C. Maddix

Citations in the corpus

• Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting (2019, methodology): “[3] fuses traditional AR models with RNNs by modeling a probabilistic distribution in an encoder-decoder fashion.”
• Deep Factors for Forecasting (2019, methodology): “Further experiments with GPs as the local model are detailed in (Maddix et al., 2018).”
• Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting (2022, methodology): “RNN-based models [35, 38, 25, 31, 32] are proposed for application in an”
• GluonTS: Probabilistic Time Series Models in Python (2019, background): “, 2003) and Deep Factor models (Maddix et al., 2018; Wang et al., 2019) which we omit due to space restrictions.”
• Deep Learning for Time Series Forecasting: Tutorial and Literature Survey (2020, background): “Other local models include Gaussian SSMs, which are computationally efficient, e.g., via a Kalman filter, and Gaussian Processes (GPs) [149, 159, 67, 27].”
• Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting (2021, methodology): “Besides, recurrent neural networks (RNNs) models are used to model the temporal dependencies for time series [36, 26, 40, 22].”
• Probabilistic Forecasting with Temporal Convolutional Neural Network (2019, methodology): “[20] propose the combination of deep neural networks and Gaussian Process.”