mlsanityData to 14 Oct 2026

DynaConF: Dynamic Forecasting of Non-Stationary Time Series

arXiv 2209.08411 ↗First posted 17 Sep 2022cs.LG stat.MLcited by 1

Not on the map. Why?

Abstract (arXiv)

Deep learning has shown impressive results in a variety of time series forecasting tasks, where modeling the conditional distribution of the future given the past is the essence. However, when this conditional distribution is non-stationary, it poses challenges for these models to learn consistently and to predict accurately. In this work, we propose a new method to model non-stationary conditional distributions over time by clearly decoupling stationary conditional distribution modeling from non-stationary dynamics modeling. Our method is based on a Bayesian dynamic model that can adapt to conditional distribution changes and a deep conditional distribution model that handles multivariate time series using a factorized output space. Our experimental results on synthetic and real-world datasets show that our model can adapt to non-stationary time series better than state-of-the-art deep learning solutions.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 33 of its 63 references that are in the map. First posted on arXiv 17 Sep 2022.

Builds on

33 of 63 references.

References · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  4. 2013Auto-Encoding Variational Bayescited by 4,053
  5. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  6. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,476
  7. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
  8. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
  9. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  10. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
  11. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 640
  12. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
21 more
  1. 2020Time Series Forecasting With Deep Learning: A Surveycited by 459
  2. 2018Conditional Neural Processescited by 426
  3. 2022Non-stationary Transformers: Exploring the Stationarity in Time Series Forecastingcited by 391
  4. 2017Variational Continual Learningcited by 339
  5. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecastingcited by 337
  6. 2018Neural Processescited by 311
  7. 2015MADE: Masked Autoencoder for Distribution Estimationcited by 307
  8. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 198
  9. 2019High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processescited by 148
  10. 2022ETSformer: Exponential Smoothing Transformers for Time-series Forecastingcited by 148
  11. 2020Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flowscited by 144
  12. 2017A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learningcited by 107
  13. 2013Rao-Blackwellised Particle Filtering for Dynamic Bayesian Networkscited by 47
  14. 2022TACTiS: Transformer-Attentional Copulas for Time Seriescited by 38
  15. 2021Temporal Latent Auto-Encoder: A Method for Probabilistic Multivariate Time Series Forecastingcited by 32
  16. 2022Learning Deep Time-index Models for Time Series Forecastingcited by 18
  17. 2021Deep Explicit Duration Switching Models for Time Seriescited by 17
  18. 2022Continual Learning for Multivariate Time Series Tasks with Variable Input Dimensionscited by 14
  19. 2020Time series forecasting with Gaussian Processes needs priorscited by 13
  20. 2020Stanza: A Nonlinear State Space Model for Probabilistic Inference in Non-Stationary Time Seriescited by 6
  21. 2022Forecasting Sparse Movement Speed of Urban Road Networks with Nonstationary Temporal Matrix Factorizationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Beyond Static Positional Encoding: Bayesian Time-aware Attention for Non-Stationary Long-term Time Series Forecastingcited by 0