mlsanityData to 7 Oct 2026

A comprehensive theoretical framework for the optimization of neural networks classification performance with respect to weighted metrics

arXiv 2305.13472 ↗First posted 22 May 2023cs.LG cs.NA math.NAcited by 3

Not on the map. Why?

Abstract (arXiv)

In many contexts, customized and weighted classification scores are designed in order to evaluate the goodness of the predictions carried out by neural networks. However, there exists a discrepancy between the maximization of such scores and the minimization of the loss function in the training phase. In this paper, we provide a complete theoretical setting that formalizes weighted classification metrics and then allows the construction of losses that drive the model to optimize these metrics of interest. After a detailed theoretical analysis, we show that our framework includes as particular instances well-established approaches such as classical cost-sensitive learning, weighted cross entropy loss functions and value-weighted skill scores.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 14 of its 31 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

14 of 31 references.

References · 14

  1. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  2. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  3. 2016Large-Margin Softmax Loss for Convolutional Neural Networkscited by 296
  4. 2018Temporal Convolutional Neural Network for the Classification of Satellite Image Time Seriescited by 76
  5. 2017On Loss Functions for Deep Neural Networks in Classificationcited by 68
  6. 2019Addressing the Loss-Metric Mismatch with Adaptive Loss Alignmentcited by 33
  7. 2015Optimizing Non-decomposable Performance Measures: A Tale of Two Classescited by 17
  8. 2021Balanced softmax cross-entropy for incremental learning with and without memorycited by 13
  9. 2021Score-oriented loss (SOL) functionscited by 11
  10. 2021Training Over-parameterized Models with Non-decomposable Objectivescited by 11
  11. 2019A New Loss Function for CNN Classifier Based on Pre-defined Evenly-Distributed Class Centroidscited by 10
  12. 2021Prediction of severe thunderstorm events with ensemble deep learning and radar datacited by 8
2 more
  1. 2021Bad and good errors: value-weighted skill scores in deep ensemble learningcited by 5
  2. 2022Operational solar flare forecasting via video-based deep learningcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025The Multiclass Score-Oriented Loss (MultiSOL) on the Simplexcited by 0
  2. 2026Don't stop me now: How Validation Criteria Affect Checkpoint Selection and Early Stoppingcited by 0
  3. 2026Weighted Score-Oriented Losses for Temporally Localized Event Predictioncited by 0