Robust Loss Functions

Ask about this topic

Overview

Robust loss functions study how to train models when data contain outliers, incorrect labels, heavy-tailed noise, or other unreliable observations. Common approaches include bounded or truncated residual losses, symmetric and generalized cross-entropy losses, divergence-based objectives, and sample reweighting; they are used in settings from regression and image classification to scientific estimation. These methods can improve performance under contamination, but their results depend on the type and level of noise and on choices such as loss shape and scale. A central challenge is gaining robustness without sacrificing clean-data accuracy, calibration, or efficiency, while establishing guarantees that match real-world benchmarks.

Latest papers

CardsList

50 papers6 papers in the last four weeks, down 14% on the four weeks before. 0.0% of all new papers.

  1. Property-Based Testing for Robust Softmax and Cross-Entropy

    Oct 27, 2026Muhammad MaazRobust Loss Functions

  2. Using Set Learning to Improve Set-Valued Classifiers on Long-tailed Data

    Oct 20, 2026Kevin Kasa, Scott C. Lowe, Graham W. TaylorSet-Valued PredictionClass-Imbalanced Learning

    University of Guelph · Vector Institute

  3. Revisiting Tabular Deep Regression: Objectives and the Limits of Global Early Stopping

    Oct 9, 2026Danil Rudenko, Georgii Bulgakov, Nikolay Kartashev +3Tabular RegressionQuantile Regression

    Yandex Research · BRAInLab · HSE University

  4. NAViLoss: An Underwater Navigation-Aware Dual-Residual Objective for Physics-Consistent Learning

    Oct 7, 2026Arup Kumar Sahoo, Itzik KleinAutonomous Underwater NavigationRobust Loss Functions

    The Hatter Department of Marine Technologies, Leon H. Charney School of Marine Sciences, University of Haifa, Haifa, 3498838, Israel

  5. Robust Local Optimization Done Right

    Oct 5, 2026James Pritts, Kevin KöserRelative Pose EstimationNonconvex Optimization

    Kiel University, Kiel, Germany

  6. Robust LassoNet: Enhancing Feature Selection in Neural Networks via Robust Loss Functions

    Sep 29, 2026Daniela De Canditiis, Italia De Feis, Paola StolfiRobust Loss FunctionsFeature Selection

    Istituto per le Applicazioni del Calcolo “Mauro Picone”, Consiglio Nazionale delle Ricerche, Via dei Taurini, 19, Roma, 00185, Italia · Istituto per le Applicazioni del Calcolo “Mauro Picone”, Consiglio Nazionale delle Ricerche, Via Pietro Castellino, 111, Napoli, 80131, Italia

  7. Beyond Sub-Gaussian Detector Scores: Robust Weighted Profile-Loss Change Point Detection for Human-LLM Text Segmentation

    Sep 29, 2026Wan Tian, Zhongyi Li, Yawen Li +3Robust Loss FunctionsChange-Point Detection

    Peking University · Beihang University · Capital Normal University +2

  8. Tail-Weight Control and Localized Generalization in Nearly Low-Rank Adversarial Classification

    Sep 20, 2026Kunyu Wang, Dehan Wang, Wenjun ChenAdversarial RobustnessRobust Loss Functions

    The Chinese University of Hong Kong · Columbia University

  9. Rethinking Class Imbalance for Single-Cell Foundation Models: A Systematic Benchmark Across Architectures and Long-Tail Loss Functions

    Sep 20, 2026Zeyu Dong, Jiahui ZhongClass-Imbalanced LearningLong-Tailed Classification

  10. Bounded Adjustment with Reliability-Guided Embedding for Imbalanced Learning with Noisy Labels

    Sep 14, 2026Mushir Akhtar, Akarsh J., M. Tanveer +1Class-Imbalanced LearningLong-Tail Learning

    Department of Mathematics, Indian Institute of Technology Indore, India · Department of Electrical Engineering, Indian Institute of Technology Indore, India

  11. Learning Sign Language Recognition under Label Noise: A Study of Noise-Robust Losses for Isolated and Continuous Settings

    Sep 11, 2026Akihisa Shitara, Yoichi OchiaiNoisy-Label LearningRobust Loss Functions

    R&D Center for Digital Nature, University of Tsukuba · Faculty of Library, Information and Media Science, University of Tsukuba · Pixie Dust Technologies, Inc.

  12. Generalization Analysis of Distributed Kernel-based Robust Gradient Descent Algorithms

    Sep 10, 2026Jun-Yi Meng, Zheng-Chu Guo, Yuan MaoKernel RegressionCommunication-Efficient Distributed Training

    School of Mathematical Sciences, Zhejiang University, Hangzhou 310058, P. R. China · College of Informatics, Huazhong Agricultural University, Wuhan 430070, P. R. China

  13. IFW-BLS: Dual-Robust Broad Learning System with Intuitionistic Fuzzy Wave Loss

    Sep 2, 2026Mushir Akhtar, M. TanveerRobust ClassificationRobust Loss Functions

    Indian Institute of Technology Indore, Simrol, Indore, India

  14. Error-Type-Aware Loss Reweighting for Robust Named Entity Recognition with Noisy LLM Labels

    Aug 31, 2026Elena Merdjanovska, Jonas Golde, Alan AkbikNamed Entity RecognitionLLM-Assisted Annotation

    Humboldt-Universität zu Berlin · Science of Intelligence

  15. Robust Broad Learning System with Wave Loss for Classification under Data Uncertainty

    Aug 30, 2026Mushir Akhtar, A. Varshney, A. Quadir +3Robust Loss FunctionsLearning with Noisy Labels

    Department of Mathematics Indian Institute of Technology Indore

  16. PERO: Efficient Robust Post-Training Foundation Models for Encrypted Traffic Classification

    Aug 16, 2026Wumei Du, Jiarong Wen, Kaiyu Zhang +5Encrypted Traffic ClassificationEncrypted Network Traffic Analysis

    National University of Defense Technology, Changsha, China

  17. Robust Dual-Model Collaborative Random Vector Functional Link Network

    Aug 13, 2026A. Quadir, A. Rahaman, Mushir Akhtar +1Learning with Noisy LabelsRobust Loss Functions

    Department of Mathematics Indian Institute of Technology Indore

  18. Sparse and robust geometric twin support vector machine via asymmetric RoBoSS loss function

    Aug 12, 2026Kai Qi, Xinji Huang, Hongchun WangNoisy-Label LearningRobust Loss Functions

    National Center for Applied Mathematics in Chongqing, Chongqing Normal University, Chongqing, 401331, China. · School of Mathematical Sciences, Chongqing Normal University, Chongqing, 401331, China.

  19. No Unique Minimizer, No Problem: On the Consistency of Robust Neural Classifiers

    Aug 9, 2026Subhabrata Majumdar, Anand Deo, Partha Pratim Saha +1Robust EstimationNeural Network Robustness

    Indian Institute of Management Bangalore · Independent Researcher · Indian Statistical Institute, Kolkata

  20. XGRVFL-MV: Residual-Coupled Graph-Embedded Multi-View Random Vector Functional Link Network with FleXi Guardian Loss

    Jul 25, 2026Yogesh Kumar, Mudasir GanaieMulti-View ConsistencyMulti-View Learning

    Department of Computer Science and Engineering, Indian Institute of Technology Ropar, Rupnagar, 140001, Punjab, India

  21. Smart predict-then-robustly-optimize

    Jul 23, 2026Aakil Caunhye, Xuefei Lu, Belen Martin-BarraganDistribution Shift RobustnessPredict-Then-Optimize

  22. Robust Losses from Univariate Base Functions for Noisy-Label Learning

    Jul 18, 2026Peng Hu, Jianwei MaNoisy-Label LearningRobust Loss Functions

    School of Mathematics, Harbin Institute of Technology, Harbin, China · Institute for Artificial Intelligence and the School of Earth and Space Sciences, Peking University, Beijing, China · Institute for Artificial Intelligence and the School of Mathematics, Harbin Institute of Technology, Harbin, China

  23. Distributionally Robust Listwise Preference Optimization

    Jul 2, 2026Xudong Wu, Jian Qian, Pangpang Liu +2LLM AlignmentDistributionally Robust Optimization

    The University of Hong Kong · Hong Kong SAR · Yale University +3

  24. Robust Diffusion Models via Divergence-Induced Weighted Denoising

    Jun 21, 2026Lei Li, Yuexiao DongNeural Network RobustnessRobust Loss Functions

    LunarAI LLC · Newark, DE 19702 · Fox School of Business +1

  25. Alternate loss functions and regression models that achieve robustness to outliers by modulating the learning rate

    Jun 20, 2026Mathew Mithra Noel, Arindam Banerjee, Yug D. Oswal +2Robust RegressionRobust Loss Functions

    aSchool of Electrical Engineering, Vellore Institute of Technology, Vellore, 632 014, Tamil Nadu, India · bErnst and Young GDS, Godrej Waterside, Ring Rd, DP Block, Sector V, Bidhannagar, Kolkata, 700 091, West Bengal, India · cSchool of Computer Science and Engineering, Vellore Institute of Technology, Vellore, 632 014, Tamil Nadu, India

  26. Neural Bayesian Anomaly Mitigation: A Robust Loss that Doubles as an Unsupervised Contamination Classifier

    Jun 15, 2026S. A. K. Leeney, W. J. Handley, H. T. J. Bevins +1Neural Network RobustnessNoisy-Label Learning

    Astrophysics Group, Cavendish Laboratory University of Cambridge · Institute of Astronomy University of Cambridge

  27. ALCL: An Adaptive Log-Correntropy Loss for Robust Learning under Non-Gaussian Noise

    Jun 14, 2026Mainak Kundu, Ria Kanjilal, Ismail UysalImage Corruption RobustnessRobust Loss Functions

    Department of Electrical Engineering, University of South Florida, Tampa, FL 33620 USA · Department of Computer Engineering, California Polytechnic State University, San Luis Obispo, CA 93407 USA

  28. Distributional Loss for Robust Classification

    Jun 11, 2026Kathleen Anderson, Thomas MartinetzRobust Loss FunctionsClassification

    Institute for Neuro- and Bioinformatics, University of Lübeck, Germany

  29. Robust and sparse support vector machine via hybrid truncated loss for supervised classification

    Jun 4, 2026Yuliang Yang, Chen Chen, Yuxiang Liu +1Multi-View LearningRobust Loss Functions

    School of Science, Beijing Forestry University, No.35 Qinghua East Road, 100083 Haidian, Beijing, China · Translational Cancer Research Center, Peking University First Hospital, No. 8 Xishiku Street, 100034 Xicheng, Beijing, China

  30. The Matching Principle: A Geometric Theory of Loss Functions for Nuisance-Robust Representation Learning

    May 21, 2026Vishal RajputDistribution Shift RobustnessJacobian Regularization

    KU Leuven