mlsanityData to 7 Oct 2026

Score-oriented loss (SOL) functions

arXiv 2103.15522 ↗First posted 29 Mar 2021cs.LG cs.NA math.NAcited by 11

Not on the map. Why?

Abstract (arXiv)

Loss functions engineering and the assessment of forecasting performances are two crucial and intertwined aspects of supervised machine learning. This paper focuses on binary classification to introduce a class of loss functions that are defined on probabilistic confusion matrices and that allow an automatic and a priori maximization of the skill scores. The performances of these loss functions are validated during the training phase of two experimental forecasting problems, thus showing that the probability distribution function associated with the confusion matrices significantly impacts the outcome of the score maximization process.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 10 of its 43 references that are in the map. First posted on arXiv 29 Mar 2021.

Builds on

10 of 43 references.

References · 10

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  3. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  4. 2016Large-Margin Softmax Loss for Convolutional Neural Networkscited by 296
  5. 2018Temporal Convolutional Neural Network for the Classification of Satellite Image Time Seriescited by 76
  6. 2017On Loss Functions for Deep Neural Networks in Classificationcited by 68
  7. 2019Addressing the Loss-Metric Mismatch with Adaptive Loss Alignmentcited by 33
  8. 2019A New Loss Function for CNN Classifier Based on Pre-defined Evenly-Distributed Class Centroidscited by 10
  9. 2021Bad and good errors: value-weighted skill scores in deep ensemble learningcited by 5
  10. 2020Machine learning as a flaring storm warning machine: Was a warning machine for the September 2017 solar flaring storm possible?cited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 1; 2023: 2; 2024: 2; 2025: 3; 2026: 2.

11 papers.

  1. 2021Prediction of severe thunderstorm events with ensemble deep learning and radar datacited by 8
  2. 2023Physics-driven machine learning for the prediction of coronal mass ejections' travel timescited by 6
  3. 2022Operational solar flare forecasting via video-based deep learningcited by 5
  4. 2023A comprehensive theoretical framework for the optimization of neural networks classification performance with respect to weighted metricscited by 3
  5. 2024Forecasting Geoffective Events from Solar Wind Data and Evaluating the Most Predictive Features through Machine Learning Approachescited by 3
  6. 2024AnyLoss: Transforming Classification Metrics into Loss Functionscited by 3
  7. 2025Multiclass threshold-based classificationcited by 1
  8. 2025Multiclass threshold-based classification and model evaluationcited by 0
  9. 2025The Multiclass Score-Oriented Loss (MultiSOL) on the Simplexcited by 0
  10. 2026Don't stop me now: How Validation Criteria Affect Checkpoint Selection and Early Stoppingcited by 0
  11. 2026Weighted Score-Oriented Losses for Temporally Localized Event Predictioncited by 0