mlsanityData to 7 Oct 2026

TimePre: Bridging Accuracy, Efficiency, and Stability in Probabilistic Time-Series Forecasting

arXiv 2511.18539 ↗First posted 23 Nov 2025cs.LG cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

We propose TimePre, a simple framework that unifies the efficiency of Multilayer Perceptron (MLP)-based models with the distributional flexibility of Multiple Choice Learning (MCL) for Probabilistic Time-Series Forecasting (PTSF). Stabilized Instance Normalization (SIN), the core of TimePre, is a normalization layer that explicitly addresses the trade-off among accuracy, efficiency, and stability. SIN stabilizes the hybrid architecture by correcting channel-wise statistical shifts, thereby resolving the catastrophic hypothesis collapse. Extensive experiments on six benchmark datasets demonstrate that TimePre achieves state-of-the-art (SOTA) accuracy on key probabilistic metrics. Critically, TimePre achieves inference speeds that are orders of magnitude faster than sampling-based models, and is more stable than prior MCL approaches.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 48 of its 75 references that are in the map. First posted on arXiv 23 Nov 2025.

Builds on

48 of 75 references.

References · 48

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2016Layer Normalizationcited by 5,579
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  7. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  8. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  9. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  10. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  11. 2019Similarity of Neural Network Representations Revisitedcited by 1,695
  12. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
36 more
  1. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
  2. 2018Group Normalizationcited by 1,514
  3. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  4. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  5. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  6. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
  7. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  8. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 820
  9. 2020Time Series Forecasting With Deep Learning: A Surveycited by 457
  10. 2024TimeMixer: Decomposable Multiscale Mixing for Time Series Forecastingcited by 333
  11. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecastingcited by 332
  12. 2016Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Predictioncited by 330
  13. 2023Long-term Forecasting with TiDE: Time-series Dense Encodercited by 327
  14. 2017A Multi-Horizon Quantile Recurrent Forecastercited by 211
  15. 2018A Convergence Analysis of Gradient Descent for Deep Linear Neural Networkscited by 180
  16. 2019Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directionscited by 172
  17. 2020Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flowscited by 142
  18. 2016Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypothesescited by 96
  19. 2019Deep Factors for Forecastingcited by 86
  20. 2016Stochastic Multiple Choice Learning for Training Diverse Deep Ensemblescited by 77
  21. 2024A Comprehensive Survey of Deep Learning for Time Series Forecasting: Architectural Diversity and Open Challengescited by 46
  22. 2019GluonTS: Probabilistic Time Series Models in Pythoncited by 45
  23. 2020Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learningcited by 34
  24. 2023TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Seriescited by 25
  25. 2024FlowTS: Time Series Generation via Rectified Flowcited by 22
  26. 2024Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealingcited by 12
  27. 2020TreeRNN: Topology-Preserving Deep GraphEmbedding and Learningcited by 7
  28. 2023Bicriteria Approximation Algorithms for the Submodular Cover Problemcited by 6
  29. 2024Winner-takes-all learners are geometry-aware conditional density estimatorscited by 6
  30. 2024Fair Submodular Covercited by 6
  31. 2025Winner-takes-all for Multivariate Probabilistic Time Series Forecastingcited by 4
  32. 2020Implicit Regularization via Neural Feature Alignmentcited by 3
  33. 2024Multiple Choice Learning for Efficient Speech Separation with Many Speakerscited by 3
  34. 2025KANMixer: a minimal KAN-centered mixer for long-term time series forecastingcited by 3
  35. 2024GAS-Norm: Score-Driven Adaptive Normalization for Non-Stationary Time Series Forecasting in Deep Learningcited by 2
  36. 2025Structured Basis Function Networks: Loss-Centric Multi-Hypothesis Ensembles with Controllable Diversitycited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026AdaptFuse: Training-Free Sequential Preference Learning via Externalized Bayesian Inferencecited by 2
  2. 2026CAPS: Cascaded Adaptive Pairwise Selection for Efficient Parallel Reasoningcited by 1
  3. 2026PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoningcited by 0