mlsanityData to 14 Oct 2026

Probabilistic Time Series Forecasting with Implicit Quantile Networks

arXiv 2107.03743 ↗First posted 8 Jul 2021cs.LG cs.AIcited by 17

Not on the map. Why?

Abstract (arXiv)

Here, we propose a general method for probabilistic time series forecasting. We combine an autoregressive recurrent neural network to model temporal dynamics with Implicit Quantile Networks to learn a large class of distributions over a time-series target. When compared to other probabilistic neural forecasting models on real- and simulated data, our approach is favorable in terms of point-wise prediction accuracy as well as on estimating the underlying temporal distribution.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 15 of its 32 references that are in the map. First posted on arXiv 8 Jul 2021.

Builds on

15 of 32 references.

References · 15

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  5. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  6. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
  7. 2014Deep Learning in Neural Networks: An Overviewcited by 770
  8. 2017A Distributional Perspective on Reinforcement Learningcited by 765
  9. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
  10. 2013Generating Sequences With Recurrent Neural Networkscited by 554
  11. 2018Implicit Quantile Networks for Distributional Reinforcement Learningcited by 369
  12. 2019High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processescited by 148
3 more
  1. 2019Fully Parameterized Quantile Function for Distributional Reinforcement Learningcited by 88
  2. 2017Deep and Confident Prediction for Time Series at Ubercited by 50
  3. 2018Autoregressive Quantile Networks for Generative Modelingcited by 31

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 5; 2024: 5; 2025: 3; 2026: 1.

17 papers.

Sort:

  1. 2022Multivariate Quantile Function Forecastercited by 19
  2. 2023Deep Learning based Forecasting: a case study from the online fashion industrycited by 12
  3. 2025Relational Conformal Prediction for Correlated Time Seriescited by 11
  4. 2023SutraNets: Sub-series Autoregressive Networks for Long-Sequence, Probabilistic Forecastingcited by 7
  5. 2025Real-Time Decision-Making for Digital Twin in Additive Manufacturing with Model Predictive Control using Time-Series Deep Neural Networkscited by 7
  6. 2022VQ-AR: Vector Quantized Autoregressive Probabilistic Time Series Forecastingcited by 3
  7. 2023Learning to Simulate: Generative Metamodeling via Quantile Regressioncited by 3
  8. 2024Training Implicit Generative Models via an Invariant Statistical Losscited by 3
  9. 2024Any-Quantile Probabilistic Forecasting of Short-Term Electricity Demandcited by 2
  10. 2024Deep Generative Quantile Bayescited by 2
  11. 2023Latent-Conditioned Policy Gradient for Multi-Objective Deep Reinforcement Learningcited by 1
  12. 2023C2FAR: Coarse-to-Fine Autoregressive Networks for Precise Probabilistic Forecastingcited by 1
5 more
  1. 2024tsGT: Stochastic Time Series Modeling With Transformercited by 1
  2. 2024VAEneu: A New Avenue for VAE Application on Probabilistic Forecastingcited by 1
  3. 2025Task-based Loss Functions in Computer Vision: A Comprehensive Reviewcited by 1
  4. 2022Auxiliary Quantile Forecasting with Linear Networkscited by 0
  5. 2026Stabilizing distribution-free probabilistic forecastscited by 0