mlsanityData to 14 Oct 2026

A Comprehensive Survey of Regression Based Loss Functions for Time Series Forecasting

arXiv 2211.02989 ↗First posted 5 Nov 2022cs.LG cs.AIcited by 33

Not on the map. Why?

Abstract (arXiv)

Time Series Forecasting has been an active area of research due to its many applications ranging from network usage prediction, resource allocation, anomaly detection, and predictive maintenance. Numerous publications published in the last five years have proposed diverse sets of objective loss functions to address cases such as biased data, long-term forecasting, multicollinear features, etc. In this paper, we have summarized 14 well-known regression loss functions commonly used for time series forecasting and listed out the circumstances where their application can aid in faster and better model convergence. We have also demonstrated how certain categories of loss functions perform well across all data sets and can be considered as a baseline objective function in circumstances where the distribution of the data is unknown. Our code is available at GitHub: https://github.com/aryan-jadon/Regression-Loss-Functions-in-Time-Series-Forecasting-Tensorflow.

Key facts. Cited by 33 papers in the map (data through 14 Oct 2026). Builds on 7 of its 42 references that are in the map. First posted on arXiv 5 Nov 2022.

Builds on

7 of 42 references.

References · 7

  1. 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 761
  2. 2020A survey of loss functions for semantic segmentationcited by 217
  3. 2019On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithmscited by 132
  4. 2016Mean Absolute Percentage Error for regression modelscited by 58
  5. 2019An Alternative Probabilistic Interpretation of the Huber Losscited by 43
  6. 2020On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regressioncited by 33
  7. 2022Statistical Properties of the log-cosh Loss Function Used in Machine Learningcited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 5; 2024: 6; 2025: 9; 2026: 12.

33 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey of Evaluation Techniques for Recommendation Systemscited by 12
  2. 2024Convergence Rate Analysis of LIONcited by 11
  3. 2025A Multimodal PDE Foundation Model for Prediction and Scientific Text Descriptionscited by 10
  4. 2023Leveraging Generative AI Models for Synthetic Data Generation in Healthcare: Balancing Research and Privacycited by 7
  5. 2024Modeling Temporal Dependencies within the Target for Long-Term Time Series Forecastingcited by 6
  6. 2024TINED: GNNs-to-MLPs by Teacher Injection and Dirichlet Energy Distillationcited by 5
  7. 2022Towards Better Long-range Time Series Forecasting using Generative Forecastingcited by 3
  8. 2023A Comparative Study of Text Embedding Models for Semantic Text Similarity in Bug Reportscited by 2
  9. 2024Enhancing Risk Assessment in Transformers with Loss-at-Risk Functionscited by 2
  10. 2025Probabilistic Neural Networks (PNNs) with t-Distributed Outputs: Adaptive Prediction Intervals Beyond Gaussian Assumptionscited by 1
  11. 2025Task-based Loss Functions in Computer Vision: A Comprehensive Reviewcited by 1
  12. 2026To See Far, Look Close: Evolutionary Forecasting for Long-term Time Seriescited by 1
21 more
  1. 2026Reshaping Action Error Distributions for Reliable Vision-Language-Action Modelscited by 1
  2. 2026Reviving Error Correction in Modern Deep Time-Series Forecastingcited by 1
  3. 2026KLAS: Using Similarity to Stitch Neural Networks for Improved Accuracy-Efficiency Tradeoffscited by 1
  4. 2026Hybrid Imbalanced Regression Through Unified Data-Level and Algorithm-Level Balancingcited by 1
  5. 2023Automated Measurement of Vascular Calcification in Femoral Endarterectomy Patients Using Deep Learningcited by 0
  6. 2023Use of Deep Neural Networks for Uncertain Stress Functions with Extensions to Impact Mechanicscited by 0
  7. 2024Bond Graphs for multi-physics informed Neural Networks for multi-variate time seriescited by 0
  8. 2024Enhancing Solar Driver Forecasting with Multivariate Transformerscited by 0
  9. 2025How to warm-start your unfolding networkcited by 0
  10. 2025DeepSeasons: a Deep Learning scale-selecting approach to Seasonal Forecastscited by 0
  11. 2025A study of Universal ODE approaches to predicting soil organic carboncited by 0
  12. 2025Early wind turbine alarm prediction based on machine learning: AlarmForecastingcited by 0
  13. 2025Real-Time Long Horizon Air Quality Forecasting via Group-Relative Policy Optimizationcited by 0
  14. 2025Robust Outlier Detection and Low-Latency Concept Drift Adaptation for Data Stream Regression: A Dual-Channel Architecturecited by 0
  15. 2026Deep Time-Series Forecasting in 10 Years: A Surveycited by 0
  16. 2026Generalizing Dynamics Modeling More Easily from Representation Perspectivecited by 0
  17. 2026Ratio-based Loss Functionscited by 0
  18. 2026IstGPT: LLM-based Anomaly Detection for Spatial-Temporal Graph in Industrial Systemscited by 0
  19. 2026ArrythML: An Autoencoder-Based TinyML Approach for On-Device Arrhythmia Detection on Resource-Constrained Embedded Systemscited by 0
  20. 2026Transformer-Based Active Learning for Data-Efficient Vaccine Epitope Selection in PRRScited by 0
  21. 2026Learning Spatio-Temporal Foundation Models from Pure Synthetic Datacited by 0