Statistical Learning Theory

Overview

Statistical learning theory asks when a learner can infer rules that work beyond its training data, and quantifies sample complexity, prediction error, and limits on what can be learned. Classical tools include VC and Littlestone dimensions, covering numbers, Rademacher complexity, stability, PAC-Bayes bounds, and minimax analysis; these provide guarantees for empirical risk minimization, online learning, kernels, and robust or private learning. Current work also studies high-dimensional and overparameterized regression, including interpolation and double descent, neural networks and Transformers, and learning under distribution shift, dependence, partial labels, or adaptive data. An enduring tension is that statistically optimal rates may be computationally unattainable, while guarantees for modern architectures often rely on idealized assumptions and may not explain practical optimization.

Latest papers

CardsList

640 papers57 papers in the last four weeks, down 31% on the four weeks before. 0.4% of all new papers.

  1. Statistical Inference with Ill-Conditioned Random Weight Neural Network Sieves

    Nov 19, 2026Giovanni Ballarin, Lyudmila Grigoryeva, Lukas GononRandom Feature MethodsStatistical Learning Theory

  2. Attention Head Specialization: Phase Transitions in Sample Complexity

    Nov 19, 2026Léo Catteau, O. Duranthon, Lenka ZdeborováAttention Head SpecializationMulti-Head Attention

  3. Extending Rademacher Complexity-Based Generalization Theory to Domain Generalization

    Nov 19, 2026Xi Wang, Liang Bai, Xian Yang +1Domain GeneralizationGeneralization Bounds

  4. Near-Quadratic Sample Compression for All VC Classes

    Nov 18, 2026Yang Cai, Vineet Gupta, Yanchen Jiang +6Sample CompressionStatistical Learning Theory

  5. Monoculture Robust Learning

    Nov 18, 2026Lee Cohen, Jon Kleinberg, Omer ReingoldStatistical Learning TheoryPAC Learning

  6. Risk-optimal active learning with informative abstention

    Nov 18, 2026Fariborz Setoudehtazangi, Geoffrey J. McLachlanActive LearningStatistical Learning Theory

  7. Error Analysis of Deep Learning

    Nov 15, 2026Yuling Jiao, Peiying Wu, Jerry Zhijian Yang +1Statistical Learning TheoryDeep Learning Optimization

  8. Training-point consistency of kernel ridge regression with varying correlation scales

    Nov 13, 2026Weiyan Mu, Shifeng Xiong, Yuming ShenKernel Ridge RegressionKernel Methods

  9. A Matching Lower Bound for Online Smooth Calibration

    Nov 11, 2026Kaixuan Ji, Quanquan GuOnline CalibrationProbability Calibration

  10. Learning Mixtures of Exponential Family

    Nov 11, 2026Mansi Sood, Devavrat ShahExponential FamilyStatistical Learning Theory

  11. A Theory of Cross-Validation Variance

    Nov 10, 2026Nathaniel S. O'Connell, Jaime L. SpeiserCross-ValidationStatistical Learning Theory

  12. Settling the Burn-in Gap: Sharp Risk Bounds for Tail-Averaged SGD in Linear Regression

    Nov 10, 2026Qingyue Zhao, Xuheng Li, Quanquan GuStochastic Gradient DescentStatistical Learning Theory

  13. Fisher-Glass Learning: Classification Bounds and Subpopulation Audits

    Nov 9, 2026El Mustapha MansouriLearning with Distribution ShiftSubgroup Robustness

  14. Generalized Adaptive Boosting and the Geometry of Mistakes

    Nov 9, 2026Marco Bressan, Nataly Brukhim, Nicolò Cesa-Bianchi +4Statistical Learning TheoryEnsemble Learning

  15. Exact Natarajan Dimension of Homogeneous Multiclass Linear Predictors

    Nov 9, 2026Jiahua Liu, Benchong LiStatistical Learning TheoryMulticlass Classification

  16. A Theoretical Reduction From Membership Inference to Reconstruction Attacks Against Learners

    Nov 8, 2026Amnon Levi, Yuval DaganTraining Data Reconstruction AttacksStatistical Learning Theory

  17. Finite-Sample and Communication-Efficient Networked Information Aggregation

    Nov 8, 2026Mohammadhossein Bateni, Zahra Hadizadeh, MohammadTaghi Hajiaghayi +2Statistical Learning TheoryRandomized Sketching

  18. Kernel-Based Learning of Analytic Operators and Parametric PDEs

    Nov 6, 2026Giovanni S. Alberti, Markus Holzleitner, Lorenzo Rosasco +1Operator LearningKernel Methods

  19. Marginal-Nonuniform Multiclass Learning

    Nov 6, 2026Nataly Brukhim, Steve Hanneke, Amirreza Shaeiri +1Statistical Learning TheoryMulticlass Classification

  20. Self-Directed Apple Tasting

    Nov 4, 2026Tanmay Devale, Reed Phillips, Arvind RamaswamiOnline LearningStatistical Learning Theory

  21. Agnostic Learning by Imitating

    Nov 3, 2026Sílvia Casacuberta, Parikshit Gopalan, Varun Kanade +3Agnostic LearningStatistical Learning Theory

  22. Conformal Prediction at Performative Equilibrium: The Price of Performativity

    Nov 3, 2026Ahmed Mahrous, Roberto Di PietroConformal PredictionPerformative Prediction