mlsanityData to 7 Oct 2026

Deep Factors for Forecasting

arXiv 1905.12417 ↗First posted 28 May 2019stat.ML cs.LGcited by 86

Not on the map. Why?

Abstract (arXiv)

Producing probabilistic forecasts for large collections of similar and/or dependent time series is a practically relevant and challenging task. Classical time series models fail to capture complex patterns in the data, and multivariate techniques struggle to scale to large problem sizes. Their reliance on strong structural assumptions makes them data-efficient, and allows them to provide uncertainty estimates. The converse is true for models based on deep neural networks, which can learn complex patterns and dependencies given enough data. 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 model. We provide both theoretical and empirical evidence for the soundness of our approach through a necessary and sufficient decomposition of exchangeable time series into a global and a local part. Our experiments demonstrate the advantages of our model both in term of data efficiency, accuracy and computational complexity.

Key facts. Cited by 86 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 21; 2022: 18; 2023: 19; 2024: 8; 2025: 11; 2026: 9.

86 papers.

Sort:

By area:

  1. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 195
  2. 2023Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Surveycited by 140
  3. 2023Dish-TS: A General Paradigm for Alleviating Distribution Shift in Time Series Forecastingcited by 91
  4. 2021Domain Adaptation for Time Series Forecasting via Attention Sharingcited by 68
  5. 2022Criteria for Classifying Forecasting Methodscited by 48
  6. 2021Causal Inference for Time series Analysis: Problems, Methods and Evaluationcited by 42
  7. 2021ScoreGrad: Multivariate Probabilistic Time Series Forecasting with Continuous Energy-based Generative Modelscited by 42
  8. 2024Retrieval Augmented Time Series Forecastingcited by 40
  9. 2023Taming Local Effects in Graph-based Spatiotemporal Forecastingcited by 37
  10. 2022Koopman Neural Forecaster for Time Series with Temporal Distribution Shiftscited by 35
  11. 2021Temporal Latent Auto-Encoder: A Method for Probabilistic Multivariate Time Series Forecastingcited by 32
  12. 2021Learning Quantile Functions without Quantile Crossing for Distribution-free Time Series Forecastingcited by 32
38 more
  1. 2022DEPTS: Deep Expansion Learning for Periodic Time Series Forecastingcited by 28
  2. 2021A Multi-view Multi-task Learning Framework for Multi-variate Time Series Forecastingcited by 21
  3. 2022Multivariate Time Series Forecasting with Latent Graph Inferencecited by 20
  4. 2023Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecastingcited by 19
  5. 2022Decoupling Local and Global Representations of Time Seriescited by 17
  6. 2021RNN with Particle Flow for Probabilistic Spatio-temporal Forecastingcited by 16
  7. 2021SSDNet: State Space Decomposition Neural Network for Time Series Forecastingcited by 15
  8. 2022Robust Probabilistic Time Series Forecastingcited by 15
  9. 2021Topological Attention for Time Series Forecastingcited by 14
  10. 2023A Transformer-based Diffusion Probabilistic Model for Heart Rate and Blood Pressure Forecasting in Intensive Care Unitcited by 14
  11. 2021Variance Reduced Training with Stratified Sampling for Forecasting Modelscited by 13
  12. 2025From Values to Tokens: An LLM-Driven Framework for Context-aware Time Series Forecasting via Symbolic Discretizationcited by 13
  13. 2021Hierarchically Regularized Deep Forecastingcited by 9
  14. 2021Deep Autoregressive Models with Spectral Attentioncited by 9
  15. 2022Instance-Based Uncertainty Estimation for Gradient-Boosted Regression Treescited by 9
  16. 2026Cast-R1: Learning Tool-Augmented Sequential Decision Policies for Time Series Forecastingcited by 9
  17. 2021Compositional Modeling of Nonlinear Dynamical Systems with ODE-based Random Featurescited by 8
  18. 2021On the benefits of maximum likelihood estimation for Regression and Forecastingcited by 8
  19. 2022Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanismscited by 8
  20. 2026MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoningcited by 8
  21. 2021Improving Neural Networks for Time Series Forecasting using Data Augmentation and AutoMLcited by 7
  22. 2022Taming the Long Tail of Deep Probabilistic Forecastingcited by 7
  23. 2023AutoXPCR: Automated Multi-Objective Model Selection for Time Series Forecastingcited by 6
  24. 2024Multivariate Probabilistic Time Series Forecasting with Correlated Errorscited by 6
  25. 2021Time Series Analysis and Modeling to Forecast: a Surveycited by 5
  26. 2021Meta-Forecasting by combining Global Deep Representations with Local Adaptationcited by 5
  27. 2022A Neural Phillips Curve and a Deep Output Gapcited by 5
  28. 2023Sequential Estimation of Gaussian Process-based Deep State-Space Modelscited by 5
  29. 2023Better Batch for Deep Probabilistic Time Series Forecastingcited by 5
  30. 2023Deep Non-Parametric Time Series Forecastercited by 5
  31. 2024Metadata Matters for Time Series: Informative Forecasting with Transformerscited by 5
  32. 2022Contextually Enhanced ES-dRNN with Dynamic Attention for Short-Term Load Forecastingcited by 4
  33. 2023Graph State-Space Models and Latent Relational Inferencecited by 4
  34. 2023Probabilistic Traffic Forecasting with Dynamic Regressioncited by 4
  35. 2021Synergetic Learning of Heterogeneous Temporal Sequences for Multi-Horizon Probabilistic Forecastingcited by 3
  36. 2022Multi-task Envisioning Transformer-based Autoencoder for Corporate Credit Rating Migration Early Predictioncited by 3
  37. 2025TimePre: Bridging Accuracy, Efficiency, and Stability in Probabilistic Time-Series Forecastingcited by 3
  38. 2022Anomaly Detection and Inter-Sensor Transfer Learning on Smart Manufacturing Datasetscited by 2

50 most cited of 86 All 86 (JSON)