Investigating the Histogram Loss in Regression

Дата публикации: 17-08-2026 20:26:00

It is becoming increasingly common in regression to train neural networks that model the entire distribution even if only the mean is required for prediction. This additional modeling often comes with performance gains, and the reasons behind the improvement are not fully known. This paper investigates a recent approach to regression, the histogram loss, which involves learning the conditional distribution of the target variable by minimizing the cross-entropy between a target distribution and a flexible histogram prediction. The resulting loss corresponds to a classification loss: a cross-entropy between the outputs and a smoothed label vector. We design theoretical and empirical analyses to determine why and when this performance gain appears and how different components of the loss contribute to it. Our results suggest that the benefits of learning distributions in this setup come from improvements in optimization rather than modeling extra information. We then demonstrate the viability of the histogram loss in common deep learning applications without the need for costly hyperparameter tuning.

Схожие новости

#	Наименование новости	Тональность	Информативность	Дата публикации
1	High-Dimensional Analysis of Gradient Flow for Extensive-Width Quadratic Neural Networks	0	8.7	17-08-2026
2	Robust training of implicit generative models for multivariate and heavy-tailed distributions with an invariant statistical loss	0	10	17-08-2026
3	End-to-End Deep Learning for Predicting Metric Space-Valued Outputs	0	10.66	17-08-2026
4	Transfer Conformal Predictive Inference for Regression	0	5.02	17-08-2026
5	High-dimensional Parameter Transfer With Fused-Regularizer	0	9.38	17-08-2026
6	Semi-supervised learning for linear extremile regression	0	6.83	17-08-2026
7	Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes	0	7.52	17-08-2026
8	Stochastic Differential Equations models for Least-Squares Stochastic Gradient Descent	0	6.66	17-08-2026
9	Statistical Learning Theory for Neural Operators	0	10.21	17-08-2026
10	Do We Need to Penalize Variance of Losses for Learning with Label Noise?	0	4.9	17-08-2026

Классификация: . Схожих патентов: 0. Схожих новостей: 10. Тональность: 0. Информативность: 5.53. Источник: jmlr.org.