Beyond Binning: Soft Task Reformulation for Deep Regression

Lawrence Stewart, Francis Bach, Quentin Berthet
Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, PMLR 300:3259-3267, 2026.

Abstract

Whilst neural networks are powerful predictors, it has been observed and theoretically analyzed that training such models by minimizing the square loss can lead to suboptimal results on regression problems, where the targets are real-valued. In this work, we propose a novel method aimed at improving test-time performance of neural networks on regression tasks. Our method is based on casting this task in a different fashion, using a target encoder, and a prediction decoder, inspired by approaches in classification and clustering. We demonstrate our method on a wide range of real-world datasets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v300-stewart26a, title = { Beyond Binning: Soft Task Reformulation for Deep Regression }, author = {Stewart, Lawrence and Bach, Francis and Berthet, Quentin}, booktitle = {Proceedings of The 29th International Conference on Artificial Intelligence and Statistics}, pages = {3259--3267}, year = {2026}, editor = {Khan, Emtiyaz and Li, Yingzhen and Solin, Arno and Ramdas, Aaditya}, volume = {300}, series = {Proceedings of Machine Learning Research}, month = {02--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v300/main/assets/stewart26a/stewart26a.pdf}, url = {https://proceedings.mlr.press/v300/stewart26a.html}, abstract = { Whilst neural networks are powerful predictors, it has been observed and theoretically analyzed that training such models by minimizing the square loss can lead to suboptimal results on regression problems, where the targets are real-valued. In this work, we propose a novel method aimed at improving test-time performance of neural networks on regression tasks. Our method is based on casting this task in a different fashion, using a target encoder, and a prediction decoder, inspired by approaches in classification and clustering. We demonstrate our method on a wide range of real-world datasets. } }
Endnote
%0 Conference Paper %T Beyond Binning: Soft Task Reformulation for Deep Regression %A Lawrence Stewart %A Francis Bach %A Quentin Berthet %B Proceedings of The 29th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2026 %E Emtiyaz Khan %E Yingzhen Li %E Arno Solin %E Aaditya Ramdas %F pmlr-v300-stewart26a %I PMLR %P 3259--3267 %U https://proceedings.mlr.press/v300/stewart26a.html %V 300 %X Whilst neural networks are powerful predictors, it has been observed and theoretically analyzed that training such models by minimizing the square loss can lead to suboptimal results on regression problems, where the targets are real-valued. In this work, we propose a novel method aimed at improving test-time performance of neural networks on regression tasks. Our method is based on casting this task in a different fashion, using a target encoder, and a prediction decoder, inspired by approaches in classification and clustering. We demonstrate our method on a wide range of real-world datasets.
APA
Stewart, L., Bach, F. & Berthet, Q.. (2026). Beyond Binning: Soft Task Reformulation for Deep Regression . Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 300:3259-3267 Available from https://proceedings.mlr.press/v300/stewart26a.html.

Related Material