Deep State Space Models for Time Series Forecasting

By Syama Sundar Rangapuram, Matthias W. Seeger, Jan Gasthaus, Lorenzo Stella, Bernie Wang, Tim Januschowski. 2018

902 citations recorded by the source corpus.

Subfields: Model Architectures, Time-Series & Forecasting

How researchers see this paper

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

In Model Architectures

In Time-Series & Forecasting

Citations in the corpus

Time-series forecasting with deep learning: a survey (2020, methodology): “p neural networks in two manners: a) to encode time-varying parameters for non-probabilistic parametric models [64, 65, 67], and b) to produce parameters of distributions used by probabilistic models [38, 40, 66]. (a) Non-probabilistic Hybrid Models With parametric time series models, forecasting eq”
N-BEATS: Neural basis expansion analysis for interpretable time series forecasting (2019, background): “Somewhat independently, the work in the modern deep learning TS forecasting developed based on variations of recurrent neural networks [8, 27, 29, 32] being largely dominated by the electricity load forecasting in the multivariate setup.”
Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting (2019, methodology): “In line with traditional methods for multi-horizon forecasting [29, 35], recent deep learning methods can be categorized into iterated approaches using autoregressive models [15, 25, 31] or direct methods using sequence-to-sequence models [13, 39].”
Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting (2019, methodology): “arima, ets implemented in R’s forecast package and the recent matrix factorization method TRMF [17], a RNN-based autoregressive model DeepAR and a RNN-based state space model DeepState [6].”
Deep Factors for Forecasting (2019, background): “In Fraccaro et al. (2017) and the recent Deep State Models (Rangapuram et al., 2018), the linear Gaussian transition structure is kept intact, so that the highly efﬁcient Kalman ﬁlter/smoother is readily applicable.”
Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting (2019, methodology): “The WAPE values from the original paper could not be directly used, as there are different values reported in [9] and [20].”
FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting (2022, methodology): “Despite the impressive results achieved by RNN-type methods (Rangapuram et al., 2018; Flunkert et al., 2017), they often suffer from the problem of gradi-* Despite the progress made by Transformer-based meth-ods for time series forecasting, they tend to fail in capturing the overall…”
FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting (2022, background): “Although RNN-like deep learning methods have made breakthroughs in time series forecasting Rangapuram et al. (2018); Salinas et al. (2020), they often suffer from problems such as gradient vanishing/exploding Pascanu et al. (2013), which limits their practical performance.”
Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting (2020, background): “A majority of such studies [16, 10, 8, 17, 18, 19, 20] rely on LSTM or GRU to model the temporal dynamics in the time series data.”
Bayesian Temporal Factorization for Multidimensional Time Series Prediction (2019, background): “Third, we would like to integrate recent advances in deep learning to better capture the complex and non-linear dynamics in modern time series data [39], [40], [41], [42], [43], [44], [45], [46].”
Multi-step Deep Autoregressive Forecasting with Latent States (2019, background): “In contrast, (Rangapuram et al., 2018) keeps the linear Gaussian structure but uses an RNN to specify the transition parameters.”
Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting (2020, methodology): “We compare the performances of StemGNN on nine public datasets, ranging from traffic, energy and electrocardiogram domains with other state-of-the-art models, including FC-LSTM [26], SFM [32], N-BEATS [19], DCRNN [17], LSTNet [14], ST-GCN [31], DeepState [21], TCN [3], Graph Wavenet [29] and DeepGLO”
Is Mamba Effective for Time Series Forecasting? (2024, neutral): “In conjunction with our work, two main areas of related work are investigated: (1) time series forecasting, and (2) applications of Mamba.”