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

2023/05/22 by Marchetti, Francesco, Guastavino, Sabrina, Campi, Cristina +2 · 1 citation
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Numerical Analysis (math.NA)

paper · doi:10.48550/arxiv.2305.13472

Abstract

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.

Cited by

• The Multiclass Score-Oriented Loss (MultiSOL) on the Simplex

Related

• Computed Decision Weights and a New Learning Algorithm for Neural Classifiers
• Training Deep Neural Networks via Direct Loss Minimization
• Regression as Classification: Influence of Task Formulation on Neural Network Features
• Evaluating the Impact of Loss Function Variation in Deep Learning for Classification
• A surrogate loss function for optimization of F_β score in binary classification with imbalanced data