mlsanityData to 14 Oct 2026

Building Bridges between Regression, Clustering, and Classification

arXiv 2502.02996 ↗First posted 5 Feb 2025stat.ML cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Regression, the task of predicting a continuous scalar target y based on some features x is one of the most fundamental tasks in machine learning and statistics. It has been observed and theoretically analyzed that the classical approach, meansquared error minimization, can lead to suboptimal results when training neural networks. In this work, we propose a new method to improve the training of these models on regression tasks, with continuous scalar targets. 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 showcase the performance of our method on a wide range of real-world datasets.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 30 of its 48 references that are in the map. First posted on arXiv 5 Feb 2025.

Builds on

30 of 48 references.

References · 30

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2017Neural Discrete Representation Learningcited by 4,712
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  5. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  6. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  7. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
  8. 2016Colorful Image Colorizationcited by 1,114
  9. 2016Pixel Recurrent Neural Networkscited by 816
  10. 2024Chronos: Learning the Language of Time Seriescited by 759
  11. 2021Revisiting Deep Learning Models for Tabular Datacited by 740
  12. 2019Solving Rubik's Cube with a Robot Handcited by 734
18 more
  1. 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 690
  2. 2022AudioLM: a Language Modeling Approach to Audio Generationcited by 616
  3. 2014OpenML: networked science in machine learningcited by 526
  4. 2018On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transportcited by 426
  5. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  6. 2017A General and Adaptive Robust Loss Functioncited by 236
  7. 2019Differentiation of Blackbox Combinatorial Solverscited by 226
  8. 2020Fast Differentiable Sorting and Rankingcited by 197
  9. 2024Stop Regressing: Training Value Functions via Classification for Scalable Deep RLcited by 144
  10. 2022Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputscited by 76
  11. 2018Improving Regression Performance with Distributional Lossescited by 67
  12. 2022Regression as Classification: Influence of Task Formulation on Neural Network Featurescited by 29
  13. 2015Robust Optimization for Deep Regressioncited by 22
  14. 2023Pathologies of Predictive Diversity in Deep Ensemblescited by 16
  15. 2023Learning a Neuron by a Shallow ReLU Network: Dynamics and Implicit Bias for Correlated Inputscited by 16
  16. 2024GeoPlant: Spatial Plant Species Prediction Datasetcited by 16
  17. 2023Differentiable Clustering with Perturbed Spanning Forestscited by 14
  18. 2024Binning as a Pretext Task: Improving Self-Supervised Learning in Tabular Domainscited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026The Universal Classifier for Graph Learningcited by 0
  2. 2026Revisiting Tabular Deep Regression: Objectives and the Limits of Global Early Stoppingcited by 0