mlsanityData to 14 Oct 2026

C2FAR: Coarse-to-Fine Autoregressive Networks for Precise Probabilistic Forecasting

arXiv 2312.15002 ↗First posted 22 Dec 2023cs.LG cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

We present coarse-to-fine autoregressive networks (C2FAR), a method for modeling the probability distribution of univariate, numeric random variables. C2FAR generates a hierarchical, coarse-to-fine discretization of a variable autoregressively; progressively finer intervals of support are generated from a sequence of binned distributions, where each distribution is conditioned on previously-generated coarser intervals. Unlike prior (flat) binned distributions, C2FAR can represent values with exponentially higher precision, for only a linear increase in complexity. We use C2FAR for probabilistic forecasting via a recurrent neural network, thus modeling time series autoregressively in both space and time. C2FAR is the first method to simultaneously handle discrete and continuous series of arbitrary scale and distribution shape. This flexibility enables a variety of time series use cases, including anomaly detection, interpolation, and compression. C2FAR achieves improvements over the state-of-the-art on several benchmark forecasting datasets.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 46 of its 89 references that are in the map. First posted on arXiv 22 Dec 2023.

Builds on

46 of 89 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  6. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  7. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  8. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  9. 2014Going Deeper with Convolutionscited by 4,241
  10. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  11. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
  12. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,501
34 more
  1. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  2. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  3. 2018Datasheets for Datasetscited by 1,386
  4. 2018Model Cards for Model Reportingcited by 1,080
  5. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
  6. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  7. 2016Pixel Recurrent Neural Networkscited by 816
  8. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 803
  9. 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 761
  10. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 607
  11. 2019Neural Spline Flowscited by 596
  12. 2017PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modificationscited by 417
  13. 2015MADE: Masked Autoencoder for Distribution Estimationcited by 307
  14. 2016On the Expressive Power of Deep Neural Networkscited by 306
  15. 2021Spectral Temporal Graph Neural Network for Multivariate Time-series Forecastingcited by 299
  16. 2015A note on the evaluation of generative modelscited by 292
  17. 2018Efficient Neural Audio Synthesiscited by 219
  18. 2017A Multi-Horizon Quantile Recurrent Forecastercited by 211
  19. 2019Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecastingcited by 161
  20. 2019High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processescited by 148
  21. 2022N-HiTS: Neural Hierarchical Interpolation for Time Series Forecastingcited by 146
  22. 2020Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flowscited by 144
  23. 2020Deep Learning for Time Series Forecasting: Tutorial and Literature Surveycited by 117
  24. 2017On the State of the Art of Evaluation in Neural Language Modelscited by 104
  25. 2016Neural Autoregressive Distribution Estimationcited by 95
  26. 2013RNADE: The real-valued neural autoregressive density-estimatorcited by 66
  27. 2019Probabilistic Forecasting with Temporal Convolutional Neural Networkcited by 63
  28. 2020The Effectiveness of Discretization in Forecasting: An Empirical Study on Neural Time Series Modelscited by 18
  29. 2021Probabilistic Time Series Forecasting with Implicit Quantile Networkscited by 17
  30. 2018ARMDN: Associative and Recurrent Mixture Density Networks for eRetail Demand Forecastingcited by 9
  31. 2021MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Datacited by 9
  32. 2021Spliced Binned-Pareto Distribution for Robust Modeling of Heavy-tailed Time Seriescited by 4
  33. 2014Effective Bayesian Modeling of Groups of Related Count Time Seriescited by 3
  34. 2020A Worrying Analysis of Probabilistic Time-series Models for Sales Forecastingcited by 3

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024RWKV-TS: Beyond Traditional Recurrent Neural Network for Time Series Taskscited by 22