Generalized Mixture Model for Extreme Events Forecasting in Time Series
Data
- URL: http://arxiv.org/abs/2310.07435v1
- Date: Wed, 11 Oct 2023 12:36:42 GMT
- Title: Generalized Mixture Model for Extreme Events Forecasting in Time Series
Data
- Authors: Jincheng Wang, Yue Gao
- Abstract summary: Time Series Forecasting (TSF) is a widely researched topic with broad applications in weather forecasting, traffic control, and stock price prediction.
Extreme values in time series often significantly impact human and natural systems, but predicting them is challenging due to their rare occurrence.
We propose a novel framework to enhance the focus on extreme events. Specifically, we propose a Deep Extreme Mixture Model with Autoencoder (DEMMA) for time series prediction.
- Score: 10.542258423966492
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Time Series Forecasting (TSF) is a widely researched topic with broad
applications in weather forecasting, traffic control, and stock price
prediction. Extreme values in time series often significantly impact human and
natural systems, but predicting them is challenging due to their rare
occurrence. Statistical methods based on Extreme Value Theory (EVT) provide a
systematic approach to modeling the distribution of extremes, particularly the
Generalized Pareto (GP) distribution for modeling the distribution of
exceedances beyond a threshold. To overcome the subpar performance of deep
learning in dealing with heavy-tailed data, we propose a novel framework to
enhance the focus on extreme events. Specifically, we propose a Deep Extreme
Mixture Model with Autoencoder (DEMMA) for time series prediction. The model
comprises two main modules: 1) a generalized mixture distribution based on the
Hurdle model and a reparameterized GP distribution form independent of the
extreme threshold, 2) an Autoencoder-based LSTM feature extractor and a
quantile prediction module with a temporal attention mechanism. We demonstrate
the effectiveness of our approach on multiple real-world rainfall datasets.
Related papers
- Unified Training of Universal Time Series Forecasting Transformers [104.56318980466742]
We present a Masked-based Universal Time Series Forecasting Transformer (Moirai)
Moirai is trained on our newly introduced Large-scale Open Time Series Archive (LOTSA) featuring over 27B observations across nine domains.
Moirai achieves competitive or superior performance as a zero-shot forecaster when compared to full-shot models.
arXiv Detail & Related papers (2024-02-04T20:00:45Z) - Learning from Polar Representation: An Extreme-Adaptive Model for
Long-Term Time Series Forecasting [10.892801642895904]
We propose Distance-weighted Auto-regularized Neural network (DAN), a novel extreme-adaptive model for long-range forecasting of stremflow enhanced by polar representation learning.
On four real-life hydrologic streamflow datasets, we demonstrate that DAN significantly outperforms both state-of-the-art hydrologic time series prediction methods and general methods designed for long-term time series prediction.
arXiv Detail & Related papers (2023-12-14T09:16:01Z) - Perceiver-based CDF Modeling for Time Series Forecasting [25.26713741799865]
We propose a new architecture, called perceiver-CDF, for modeling cumulative distribution functions (CDF) of time series data.
Our approach combines the perceiver architecture with a copula-based attention mechanism tailored for multimodal time series prediction.
Experiments on the unimodal and multimodal benchmarks consistently demonstrate a 20% improvement over state-of-the-art methods.
arXiv Detail & Related papers (2023-10-03T01:13:17Z) - Generative Time Series Forecasting with Diffusion, Denoise, and
Disentanglement [51.55157852647306]
Time series forecasting has been a widely explored task of great importance in many applications.
It is common that real-world time series data are recorded in a short time period, which results in a big gap between the deep model and the limited and noisy time series.
We propose to address the time series forecasting problem with generative modeling and propose a bidirectional variational auto-encoder equipped with diffusion, denoise, and disentanglement.
arXiv Detail & Related papers (2023-01-08T12:20:46Z) - Multi-scale Attention Flow for Probabilistic Time Series Forecasting [68.20798558048678]
We propose a novel non-autoregressive deep learning model, called Multi-scale Attention Normalizing Flow(MANF)
Our model avoids the influence of cumulative error and does not increase the time complexity.
Our model achieves state-of-the-art performance on many popular multivariate datasets.
arXiv Detail & Related papers (2022-05-16T07:53:42Z) - Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios.
We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
arXiv Detail & Related papers (2022-04-13T12:43:12Z) - Deep Autoregressive Models with Spectral Attention [74.08846528440024]
We propose a forecasting architecture that combines deep autoregressive models with a Spectral Attention (SA) module.
By characterizing in the spectral domain the embedding of the time series as occurrences of a random process, our method can identify global trends and seasonality patterns.
Two spectral attention models, global and local to the time series, integrate this information within the forecast and perform spectral filtering to remove time series's noise.
arXiv Detail & Related papers (2021-07-13T11:08:47Z) - Learning Interpretable Deep State Space Model for Probabilistic Time
Series Forecasting [98.57851612518758]
Probabilistic time series forecasting involves estimating the distribution of future based on its history.
We propose a deep state space model for probabilistic time series forecasting whereby the non-linear emission model and transition model are parameterized by networks.
We show in experiments that our model produces accurate and sharp probabilistic forecasts.
arXiv Detail & Related papers (2021-01-31T06:49:33Z) - Deep Distributional Time Series Models and the Probabilistic Forecasting
of Intraday Electricity Prices [0.0]
We propose two approaches to constructing deep time series probabilistic models.
The first is where the output layer of the ESN has disturbances and a shrinkage prior for additional regularization.
The second approach employs the implicit copula of an ESN with Gaussian disturbances, which is a deep copula process on the feature space.
arXiv Detail & Related papers (2020-10-05T08:02:29Z) - Mixture Density Conditional Generative Adversarial Network Models
(MD-CGAN) [1.0312968200748118]
We present the Mixture Density Generative Adversarial Model (MD-CGAN) with a focus on time series forecasting.
By using a Gaussian mixture model as the output distribution, MD-CGAN offers posterior predictions that are non-Gaussian.
arXiv Detail & Related papers (2020-04-08T03:55:30Z) - Multivariate Probabilistic Time Series Forecasting via Conditioned
Normalizing Flows [8.859284959951204]
Time series forecasting is fundamental to scientific and engineering problems.
Deep learning methods are well suited for this problem.
We show that it improves over the state-of-the-art for standard metrics on many real-world data sets.
arXiv Detail & Related papers (2020-02-14T16:16:51Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.